The adapted Posner spatial cue-target paradigm was used to explore the relationship between exogenous temporal attention caused by rhythm and endogenous and exogenous spatial attention. The study was divided into two experiments. In Experiment 1, 33 participants used arrow cues to orient endogenous spatial attention and rhythm to orient exogenous temporal attention. In Experiment 2, with 29 participants, exogenous spatial attention was directed by highlighting the cue box. Exogenous temporal attention was directed by rhythm. Experiment 1 indicated that RTs were faster for attended targets than the unattended. The main effect of temporal attention was significant, with RTs being faster for synchrony and late compared to early. RTs were faster for late compared to synchrony. The main effect of stimulus repetition was significant, with faster RTs for targets when the rhythmic cue consisted of five compared to four. The interaction between spatial attention and temporal attention was not significant. Experiment 2 demonstrated that exogenous spatial attention only exhibited IOR under early four stimulus repetitions. The main effect of temporal attention was significant, with RTs being faster for synchrony and late compared to early. The main effect of stimulus repetition was significant, with faster RTs for targets when the rhythmic cue consisted of five compared to four. The interaction between spatial attention and temporal attention was significant. The results indicated that rhythmic temporal attention supported foreperiod effects. Exogenous temporal attention and endogenous spatial attention independently affect behavior, while exogenous temporal attention and exogenous spatial attention mutually influenced behavior.

The issue of polarization, as opposed to inequality, has been little explored for European countries. in this paper, using harmonized data produced by Luxembourg Income Study Database, observes income trends for 12 European countries, showing an increase in polarization in many of the countries considered. the drivers that led to this concentration of income are also analyzed, noting heterogeneous factors within countries.

The article presents the concept of sustainable development of socio-cultural capital with particular emphasis of the role of cultural institutions as factors influencing their development in a human being. In the article, the concept of social capital and cultural capital have been treated as complementary to each other, which is why they have been identified as a socio-cultural capital. Sustainable development of this capital in many cities of the world meets a number of problems reflected in the quality of life of its residents. In this article, a part of the town is analyzed which, due to political decisions made at the end of the First World War, has been divided for a hundred years into Cieszyn on the Polish side of the border and Czech Cieszyn (Český Těšín). This area is an example of how historical, political, demographic and educational conditions form the basis for the quality of socio-cultural capital. It is also an example of cooperative activities between local government institutions and third sector organizations. Despite many differences between the residents of Cieszyn and Czech Cieszyn, the conducted analysis points to the formation of a socio-cultural capital of a combining character, according to how Robert Putnam wrote about such phenomena, without neglecting the diversity of goals and interaction groups.

The issues of metallic scrap management and its utilization in manufacturing plants are nowadays intensely considered to address essential sustainability guidelines. Efficient recycling procedure for shop floor metallic scrap is not yet available because of abundance and contamination of nonmetallic constituents. Other ferrous metallic scrap are melted and purified during secondary steelmaking to get products in the form of blooms and billets are obtained. This study illustrates the potential of powder technology (powder metallurgy (PM) and metal injection molding (MIM)) based process for solid-state recycling and attainment of usable products. Industrially downgraded grinding sludge is pulverized and used as a raw material. Results showed properties of sintered parts are significantly improved due to in-situ reduction and densification during sintering. Recyclability Index (RI) was created to compare the effect of process variables on obtained products. Based on RI, recycled ferrous parts have about 70% comparable properties with equivalent pure iron parts. Complex reduction and sintering behavior in MIM, particularly, diffusion and pore volume kinetics limits applicability of MIM with this recycling approach. However, few industrial parts were developed and manufactured by PM based approach to validate the applicability of this novel recycling-cum-manufacturing process for the production of porous parts.

Underwater image often exhibit detail blurring and color distortion due to light scattering, impurities, and other influences, obscuring essential textures and details. This presents a challenge for existing super-resolution techniques in identifying and extracting effective features, making high-quality reconstruction difficult. This research aims to innovate underwater image super-resolution technology to tackle this challenge. Initially, an underwater image degradation model was created by integrating random subsampling, Gaussian blur, mixed noise, and suspended particle simulation to generate a highly realistic synthetic dataset, thereby training the network to adapt to various degradation factors. Subsequently, to enhance the network's capability to extract key features, improvements were made based on the symmetrically structured Blind Super-Resolution Generative Adversarial Network (BSRGAN) model architecture. An attention mechanism based on energy functions was introduced within the generator to assess the importance of each pixel, and a weighted fusion strategy of adversarial loss, reconstruction loss, and perceptual loss was utilized to improve the quality of image reconstruction. Experimental results demonstrate that the proposed method achieved significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Underwater Image Quality Measure (UIQM) by 0.85 dB and 0.19, respectively, significantly enhancing the visual perception quality and indicating its feasibility in super-resolution applications.

Microscopic vision plays an important role in automated micro-assembly. However, some uncertain factors in the assembly process, such as occlusion and stains can lead to the mistakes of feature extraction. Herein, to solve the problem, the deep learning techniques are introduced into the feature recognition tasks, focusing on the attention mechanism and visualizing CNNs for DL-based microscopic vision. The main contributions are summarized as follows: The CBAM attention mechanism is combined with the YOLOv5 algorithm to improve the accuracy and robustness of feature extraction. The micropart feature occlusion experiment results show that at 70% occlusion degree, YOLOV5-CBAM can reach 97.9% [email protected], which is 4.6% higher than the original one. Visualization analysis of DL-based model is conducted using Grad-CAM to make the decision result more transparent and avoid potential visual detection risks during assembly. The heatmap matching degree between GT area and high-light area is increased by 27.81% on average, which further verify the effectiveness of attention mechanism in micropart feature localization. Additionally, micropart surface stain and droplet quality classification models based on ResNet50 are trained to replace the manual sorting. The visual results are consistent with human eye discernment and judgement, confirming the reliability of parts and droplets sorting.

The learning equations of an ANN are presented, giving an extremely concise derivation based on the principle of backpropagation through the descendent gradient. Then, a reflection is developed on the dual attention network that applies the learning equations and coordinates subnetworks toward purposeful behaviors. Speculation is made on possible developments of functionalities that could provide additional skills and at the same time shed light on competencies typical of ``natural intelligence".

In contemporary narratives, the rural and regional identities of a place, as judged by its inhabitants’ sense of belonging, continue to be important points that need to be (re)considered when discussing places as instruments for local development. This paper pushes forward these debated and explores the construction of rural and regional identity in Romania with the help of a case study that focuses on two rural communities situated on opposite sides of the river Mureș. Based on participant and ethnographic observation and making use of a qualitative analysis, this paper highlights the most significant features of the local cultural identities expressed by the two sets of people, which often coincide with the most important characteristics attributed to the regions separated by the river Mureș. The results of this study underline the dividing role of a river in the preservation of rural and regional identity. They also demonstrate that rural identity construction along the river has generated both rural development opportunities and various risks.

Contemporary literature dealing with the governance and exploitation of common-pool natural resources was initiated by Elinor Ostrom in 1990, and has been growing fast ever since. On the contrary, within the same research stream, the study of the presence and economic role of common resources in entrepreneurial organizations is, to date, under-researched. This work endeavors to fill some gaps in this research perspective by: (i) spelling out a new-institutionalist framework for the analysis of the accumulation and governance of common capital resources within organizational boundaries; (ii) considering co-operative enterprises as the organizational form that, on the basis of historical record, and of behavioral and institutional characteristics, demonstrated to be most compatible with a substantial role for common and non-divided asset-ownership and with its governance thereof; (iii) evidencing and explaining the strong connection between cooperative longevity and the presence of non-divided asset ownership. The economic forces influencing the optimal level of self-financed common capital resources in co-operatives are enquired. Conclusions to the paper evidence the main reasons why the new approach can better explain than preceding ones the economic sustainability and longevity of cooperative enterprises.

In today’s fast paced, attention-demanding society, executive functions and attentional resources are often taxed. Individuals need ways to sustain and restore these resources. We first review the concepts of attention and restoration, as instantiated in Attention Restoration Theory (ART). ART emphasizes the role of nature in restoring attention. We then discuss essentials of experiments on the causal influences of nature. Next, we expand the concept of ART to include modern, designed environments. We propose a wider perspective termed attentional ecology, in which attention behavior is viewed within a larger system involving the human and their interactions over time with environmental demands. When the ecology is optimal, mental functioning can be a positive “flow” that is productive, sustainable for the individual, and sometimes creative.

One of the most crucial elements in deeply understanding humans on a psychological level is manifested through facial expressions. The analysis of a human behavior can be informed by their facial expressions, making it essential to employ indicators such as expression (Expr), valence-arousal (VA), and action units (AU). In this paper, we introduce the method proposed in the Challenge of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW) at CVPR 2024. Our proposed method utilizes the multi-modal Aff-wild2 dataset, which is splitted into spatial and audio modalities. For the spatial data, we extract features using a SimMiM model that was pre-trained on a diverse set of facial expression data. For the audio data, we extract features using a WAV2VEC model. To fusion the extracted spatial and audio features, we employed the cascaded cross-attention mechanism of a transformer.

In recent years, graph neural networks (GNNs) have become a promising method for analyzing data structured in graph format. By considering connections between entities in a graph, GNNs are able to extract valuable insights. One notable variation of GNN is the graph attention network (GAT), which employs the attention mechanism and has demonstrated promising performance in various applications. However, its ability to incorporate feature information from nodes beyond the immediate neighborhood is limited, leading to degraded performance on heterophilic data. To address this limitation, this thesis proposes a novel attention-based model, namely the Directional Graph Attention Network (DGAT). This model combines the feature-based attention with the global directional information extracted from the graph topology, as inspired by the Directional Graph Network (DGN). A new class of Laplacian matrices is proposed and an existing theoretical result on DGN is extended. This extension bridges a gap in the literature. The experimental results presented in the thesis, based on nine real-world benchmarks and ten synthetic data sets, demonstrate the superiority of the proposed DGAT model compared to the GAT baseline model. Particularly on heterophilic data sets, DGAT showed a notable average increase of approximately 35% in node classification tasks across all heterophilic real-world data sets. In addition, DGAT outperforms GAT by an average margin of around 51% in all ten synthetic data sets with various levels of heterophily

To efficiently use its finite resources, the visual system selects for further processing only a subset of the rich sensory information. Visual masking and spatial attention control the information transfer from visual sensory-memory to visual short-term memory. There is still a debate whether these two processes operate independently or interact, with empirical evidence supporting both arguments. However, recent studies pointed out that earlier studies showing significant interactions between common-onset masking and attention suffered from ceiling and/or floor effects. Our review of previous studies reporting metacontrast-attention interactions revealed similar artifacts. Therefore, we investigated metacontrast-attention interactions by using an experimental paradigm in which ceiling/floor effects were avoided. We also examined whether metacontrast masking is differently influenced by endogenous and exogenous attention. We analyzed mean absolute-magnitude of response-errors and their statistical distribution. Our results support the hypothesis that metacontrast and endogenous/exogenous attention are largely independent with negligible likelihood for interactions. Moreover, statistical modeling of the distribution of response-errors suggests weak interactions modulating the probability of “guessing” behavior for some observers in both types of attention. Nevertheless, our data suggest that any joint effect of attention and metacontrast can be adequately explained by their independent and additive contributions.

Anomaly detection and segmentation aim at distinguishing abnormal images from normal images and further localizing the anomalous regions. Feature reconstruction based method has become one of the mainstream methods for this task. This kind of method has two assumptions: (1) The features extracted by neural network is a good representation of the image. (2) The autoencoder solely trained on the features of normal images cannot reconstruct the features of anomalous regions well. But these two assumptions are hard to meet. In this paper, we propose a new anomaly segmentation method based on feature reconstruction. Our approach mainly consists of two parts: (1) We use a pretrained vision transformer (ViT) to extract the features of the input image. (2) We design a self-attention autoencoder to reconstruct the features. We regard that the self-attention operation which has a global receptive field is beneficial to the methods based on feature reconstruction both in feature extraction and reconstruction. The experiments show that our method outperforms the state-of-the-art approaches for anomaly segmentation on the MVTec dataset. It is both effective and time-efficient.

The initial valves of two Cymbella species are observed under the scanning electron microscope and the perizonium ultrastructure of Cymbella is revealed for the first time. The perizonium is composed of alternate nodes and internodes and lacks transverse perizonium bands. Four new species, Cymbella apiculatophora sp. nov., C. hunanensis sp. nov., C. juglandis sp. nov. and C. menyuanensis sp. nov., are described using light and scanning electron microscope from epilithon samples collected in rivers from Hunan and Qinghai Provinces, China. Cymbella menyuanensis is a typical Cymbella species that closely resembles species in the group around C. cymbiformis Agardh, the lectotype species of the genus. Cymbella apiculatophora is similar to C. sinensis Metzeltin & Krammer while Cymbella hunanensis is closer to the C. hustedtii Krasske group. The last species, C. juglandis, has a cymbelloid valve outline, obscured intermissio, internal occlusions of areolae, dorsally deflected distal raphe fissures, and a divided APF at each apex, and does not appear to belong to any group. In addition, new observations on C. cf. excisiformis Krammer and C. hustedtii are reported. The current concept of the genus Cymbella does not represent a monophyletic group as shown by molecular phylogenetic analyses. However, these analyses are still at the preliminary stage and are not yet sufficient to support a complete revision of the genus. Thus, although extremely diverse ultrastructural features are observed in the six Cymbella species investigated in this paper, we prefer to keep them within Cymbella at this moment for the sake of nomenclatural stability.

The neural system has limited resources to interact with the environment, and this is where attention comes into play. Attention is a complex process that provides numerous benefits, but there has been a longstanding debate about the mechanisms involved in attentional orientation. Two widely proposed mechanisms are top-down and bottom-up, which relate to the organism's current behavioral goal and the salience of environmental stimuli, respectively. However, distinguishing between these mechanisms can be challenging in both behavioral and neural studies. This review introduces a new conceptualization in which both top-down and bottom-up mechanisms are viewed as aspects of the same process. This unified approach aims to prepare the organism to face stimuli and events based on its prior experiences, immediate (the current task that he/she is aware of), and innate (to be alive) demands.

One of the most leading causes of death worldwide is Colorectal cancer(CRC). Polyp segmentation is the most important detected measure for preventing CRC. However, there is still a missing rate for diminutive polyps and multiple ones. In order to solve the phenomenon, we propose to introduce auxiliary attention module(AAM) that can enhance the learning of features related to multiple and diminutive polyps by focusing more on the located and detailed information. Meanwhile, we design to decrease missed rate of multiple and diminutive polyps by implementing an area adaptive loss(AAL) which adapts the weight according to the area and the number of polyps. Our proposed novel AAM and AAL concentrates on training with hard examples and localized information. To evaluate the effectiveness and generalization ability of our proposed model, We utilize three different datasets of variable sizes and a cross dataset. Our proposed method achieves the best results on the Kvasir-SEG dataset, the CVC-ClinicDB dataset and the cross dataset, particularly for the Kvasir-Sessile dataset consisting of small,flat and diminutive polyps. Extensive experimental results show that our proposed DoubleAANet surpass the performance of all existing state-of-the-art segmentation methods.

Attention Deficit Hyperactivity Disorder (ADHD) it is known as a neuropsychiatric disorder. Anatomicaly components with implications in this previously mentioned disorder, are the anterior cingulate gyrus and dorsolateral prefrontal cortex (DLFPC) that are are found having a role in appearing this disease. ADHD is associated with cognitive and functional deficits that relate to diffuse abnormalities in the brain. ADHD is a specific pathology in children but may persisit to youth and also not so hard to find to adults.Till now, hard to find the curative treatment knowing ADHD as a neuropsychiatric disorder with enlarge unknown scientific points. Genetic and environmental component play an important role in diagnosis. Patients life style, a relevant history of individual geneticsand environmental factors are important in diagnosisThe management of ADHD, is also an important part togeter with future trends.

Teeth segmentation plays a pivotal role in dental diagnosis, treatment, planning, and the development of computer-aided dental systems. It enables precise identification and analysis of dental structures, aiding in detecting dental abnormalities, measuring tooth dimensions, and assessing oral health conditions. Accurate teeth segmentation also facilitates the automation of dental workflows, leading to improved efficiency and reduced human error. Artificial Intelligence (AI) has witnessed rapid advancements, with various approaches developed or enhanced. While Convolutional Neural Networks (CNNs) have been widely used in medical image segmentation, the U-Net architecture has emerged as a standout performer due to its exceptional segmentation capabilities. This paper presents a proof of concept for the Attention U-Net architecture, as previously used in [1], applied to teeth segmentation. The study demonstrates the superior performance of this network in accurately segmenting teeth using a newly available benchmark dataset called Tufts Dental X-Ray Dataset. When trained and tested on 10-fold cross-validation, the model achieved an average dice coefficient of 95.01%, intersection over union of 90.6%, and pixel accuracy of 98.82%. These scores surpass those of all other networks implemented on the same dataset. By leveraging the Attention U-Net architecture, our research showcases the potential of advanced AI techniques in dental radiography. The findings contribute to the ongoing efforts to develop automated systems to assist dental professionals in their clinical practice.

This review explores the complex interrelationships between emotion, attention, and behavior, drawing upon empirical evidence from psychological, neuroscientific, and clinical studies. It delves into the neural mechanisms that underlie these interactions, with a focus on key brain regions such as the prefrontal cortex and amygdala. Clinical cases involving stroke and attention-deficit/hyperactivity disorder (ADHD) are examined to illustrate the real-world implications of these cognitive interactions. The review also discusses the impact of effective emotion regulation strategies and the role of attention as a cognitive mechanism that influences both emotion and behavior. Neuroimaging studies, particularly functional MRI, are highlighted for their role in providing a deeper understanding of these intricate relationships. The review concludes by emphasizing the importance of this triadic relationship in adaptive functioning and its broader implications for mental health, interpersonal relationships, and quality of life.

The demand for precise indoor localization services is steadily increasing. Among various methods, fingerprint-based indoor localization has become a popular choice due to its exceptional accuracy, cost-effectiveness, and ease of implementation. However, its performance degrades significantly as a result of multipath signal attenuation and environmental changes. In this paper, we propose an indoor localization method based on fingerprints using self-attention and long short-term memory (LSTM). By integrating a self-attention mechanism and LSTM network, the proposed method exhibits outstanding positioning accuracy and robustness in diverse experimental environments. The performance of the proposed method is evaluated under two different experimental scenarios, which involve 2D and 3D moving trajectories, respectively. The experimental results demonstrate that our approach achieves an average localization error of 1.76 m and 2.83 m in the respective scenarios, outperforming the existing state-of-the-art methods by 42.67% and 31.64%.

FV (finger vein) identification is a biometric identification technology that extracts the features of FV images for identity authentication. To address the limitations of CNN-based FV identification, particularly the challenge of small receptive fields and difficulty in capturing long-range dependencies, an FV identification method Let-Net(Large kernel and attention mechanism Network) was introduced, which combines local and global information. Firstly, Let-Net employs large kernels to broaden the receptive field and incorporates depthwise convolution with residual connections to reduce parameter count. Secondly, Let-Net integrates an attention mechanism to enhance the information flows in channels and spaces for more comprehensive and distinctive FV feature extraction. The experimental results on nine public datasets show that Let-Net has excellent identification performance, and the EER and accuracy rate on the FV_USM dataset can reach 0.04% and 99.77%. The parameter number and FLOPs of Let-Net are only 0.89M and 0.25G, which means that the time cost of training and reasoning of the model is low, and it is easier to deploy and integrate into various applications.

Multispectral image (MSI) and hyperspectral image (HSI) fusion (MHIF) aims to address the challenge of acquiring high-resolution (HR) HSI images. This field combines a low-resolution (LR) HSI with an HR-MSI to reconstruct HR-HSI. Existing methods directly utilize transformers to perform feature extraction and fusion. Despite the demonstrated success, there exist two limitations: 1) Employing the entire transformer model for feature extraction and fusion fails to fully harness the transformer’s potential in integrating the spectral of the HSI and spatial information of the MSI. 2) HSI has a strong spectral correlation and exhibits sparsity in the spatial domain. Existing transformer-based models do not optimize this physical property, which makes their methods prone to spectral distortion. To accomplish these issues, this paper introduces a novel framework for MHIF called Sparse Mix-Attention Transformer (SAMformer). Specifically, to fully harness the advantages of the Transformer architecture, we propose a Spectral Mix Attention Block (SMAB), which concatenates the keys and values extracted from LR-HSI and HR-MSI to create a new multi-head attention module. This design facilitates the extraction of detailed long-range information across spatial and spectral dimensions. Besides, to address the spatial sparsity inherent in HSI, we incorporated a sparse mechanism within the core of SMAB called Sparse Spectral Mix Attention Block (SSMAB). In the SSMAB, we compute attention maps from queries and keys and select the K highly correlated values as the sparse attention map. This approach enables us to achieve a sparse representation of spatial information while eliminating spatially disruptive noise. Extensive experiments conducted on three benchmark datasets, namely Cave, Harvard, and Pavia Center, demonstrate the SMAformer method outperforms state-of-the-art methods.

Recently deep cross-modal hashing networks have received increasing interests due to its superior query efficiency and low storage cost. However, most of existing methods concentrate less on hash representations learning part, which means the semantic information of data cannot be fully used. Furthermore, they may neglect the high-ranking relevance and consistency of hash codes. To solve these problems, we propose a Self-Attention and Adversary Guided Hashing Network (SAAGHN). Specifically, it employs self-attention mechanism in hash representations learning part to extract rich semantic relevance information. Meanwhile, in order to keep invariability of hash codes, adversarial learning is adopted in the hash codes learning part. In addition, to generate higher-ranking hash codes and avoid local minima early, a new batch semi-hard cosine triplet loss and a cosine quantization loss are proposed. Extensive experiments on two benchmark datasets have shown that SAAGHN outperforms other baselines and achieves the state-of-the-art performance.

Music and language are hypothesized to share neural resources, particularly at the level of syntax processing. Recent reports suggest that attention modulates this sharing of neural resources, but the time-course of the effects of attention, and the degree to which attention operates similarly on music and language, are yet unclear. In this EEG study we manipulate the syntactic structure of simultaneously presented musical chord progressions and garden-path sentences in a modified rapid serial visual presentation paradigm, while varying top-down attentional demands to the two modalities. The Early Right Anterior Negativity (ERAN) was observed in response to both attended and unattended musical syntax violations. In contrast, an N400 was only observed in response to attended linguistic syntax violations, and a P3 only in response to attended musical syntax violations. Results show that top-down allocation of attention indeed affects the processing of syntax in both music and language, with different neural resources acting upon the two modalities particularly at later stages of cognitive processing. However, the processing of musical syntax at an earlier stage of the perceptual-cognitive pathway, as indexed by the ERAN, is partially automatic, and is strongly indicative of separate neural resources for music and language.

：Non-Euclidean data, such as social networks, and citation relationships between documents, has node information and structural information. Graph Convolutional Network(GCN) can automatically learn node features and association information between nodes. The core ideology of the graph convolutional network is to aggregate node information by using edge information, thereby generating a new node feature. In the process of updating node features, there are two core influencing factors. One is the number of neighboring nodes of the central node, the other is the contribution of the neighboring nodes to the central node. Due to the previous GCN methods not simultaneously considering the numbers and different contributions of neighboring nodes to the central node, we design the Adaptive Attention Mechanism(AAM). To further enhance the representational capability of the model, we utilize Multi-Head Graph Convolution(MHGC). Finally, we adopt cross-entropy(CE) loss function to describe the difference between the predicted results of node categories and the ground truth (GT). Combined with backpropagation, this ultimately achieves accurate node classification. Based on AAM, MHGC and CE, we contrive the novel Graph Adaptive Attention Network (GAAN). Experiments show that the classification accuracy has achieved outstanding performances on Cora, Citeseer and Pubmed datasets.

Remote sensing imagery is of great significance for policy decisions, especially for disaster assessment and disaster relief. To ensure the privacy and inviolability of personal buildings, the information containing these buildings must be anonymized during the remote sensing mapping process. Traditional processing methods for these targets in remote sensing mapping are mainly based on manual retrieval and image editing tools, which are inefficient. Deep learning provides a new direction for target hiding. Although the image inpainting method based on deep learning is faster than the manual method, the cost of training calculation is a disadvantage. And the element-wise product operation used in the model increases the risk of vanished or exploded gradients. We propose a Residual Attention Target Hiding (RATH) model for remote sensing target hiding based on deep learning. RATH uses residual attention modules to replace gated convolutions, reducing parameters and mitigating gradient issues. The residual attention module preserves gated convolution performance but provides an adjustable kernel size. RATH retains gated convolutions for dynamic feature selection and balances model depth and width. Furthermore, this paper modifies the contextual attention layer by adjusting the fusion process to enlarge the fusion patch size. Finally, we extend the edge-guided function to preserve the original target information and confound viewers. Ablation studies on an open dataset prove RATH’s efficiency for image inpainting and target hiding. RATH achieves state-of-the-art results with lower complexity. And it has the highest similarity for edge-guided target hiding. RATH enables robust, efficient target hiding for privacy protection in remote sensing imagery while balancing performance and complexity. Experiments show RATH's superiority over existing methods in hiding arbitrary-shaped targets.

The spread of 2019 novel coronavirus disease (COVID-19) throughout the world has been a severe challenge for public health. The human angiotensin-converting enzyme 2 (ACE2) has a remarkably high affinity binding to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). By the search for network database and re-analysis of pubic data, we found the level of ACE2 expression in adipose tissue was higher than that in lung tissue, which indicated the adipose tissue might be vulnerable to SARS-CoV-2 as well; the levels of ACE2 expressed by adipocytes and adipose progenitor cells were similar between non-obese individuals and obese individuals, but obese individuals have more adiposes so as to increase the number of ACE2-expressing cells; the expression of ACE2 in tumor tissues posed by five different types of cancers increased significantly compared with that in adjacent tissues. Thus, we suggest that more attentions might be given to obese individuals and the five types of cancer patients during the outbreak of COVID-19.

Emotion detection holds significant importance in facilitating human-computer interaction, enhancing the depth of engagement. By integrating this capability, we pave the way for forthcoming AI technologies to possess a blend of cognitive and emotional understanding, bridging the divide between machine functionality and human emotional complexity. This progress has the potential to reshape how machines perceive and respond to human emotions, ushering in an era of empathetic and intuitive artificial systems. This paper introduces a novel approach to multimodal emotion recognition, seamlessly integrating speech and text modalities to accurately infer emotional states. Employing CNNs, we meticulously analyze speech using Mel spectrograms, while a BERT-based model processes the textual component, leveraging its bidirectional layers for profound semantic comprehension. The outputs from both modalities are combined using an attention-based fusion mechanism that optimally weighs their contributions. The proposed method undergoes meticulous testing on two distinct datasets: Carnegie Mellon University’s Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) dataset and the Multimodal Emotion Lines Dataset (MELD). The results demonstrate superior efficacy compared to existing frameworks, achieving an accuracy of 88.4% and an F1-score of 87.9% on the CMU-MOSEI dataset, and a notable weighted accuracy (WA) of 67.81% and a weighted F1 (WF1) score of 66.32% on the MELD dataset. This comprehensive system offers precise emotion detection and introduces several significant advancements in the field.

Water distribution networks are often susceptible to pipeline leaks caused by mechanical damages, natural hazards, corrosion, and other factors. This paper focuses on the detection of leaks in water distribution networks (WDN) using a data-driven approach based on machine learning. A hybrid Autoencoder neural network (AE) is developed, which utilizes unsupervised learning to address the issue of unbalanced data (as anomalies are rare events). The AE consists of a 3DCNN encoder, a ConvLSTM decoder, and a ConvLSTM future predictor, making the anomaly detection robust. Additionally, spatial, and temporal attention mechanisms are employed to enhance leak localization. The AE first learns the expected behavior and subsequently detects leaks by identifying deviations from this expected behavior. To evaluate the performance of the proposed method, the Water Network Tool for Resilience (WNTR) Simulator is utilized to generate water pressure and flow rate data in a water supply network. Various conditions such as fluctuating water demands, data noise, and the presence of leaks are considered using the pressure-driven demand (PDD) method. Datasets with and without pipe leaks are obtained, where the AE is trained using the dataset without leaks and tested using the dataset with simulated pipe leaks. The results, based on a benchmark WDN and a confusion matrix analysis, demonstrate that the proposed method successfully identifies leaks in 96% of cases and a false positive rate of 4% compared to a random forest model baseline based on supervised learning with a false positive rate of 15% due to unbalanced data. Furthermore, a real case study demonstrates the applicability of the developed model for leak detection in operational conditions of water supply networks using inline sensor data.

Using digital media has become the most popular leisure activity for children and adolescents. The effects of digital media use on the developing brain and cognitive processes of children are subject to debate. Here, we examine the effect of digital media use on attention subdomains in children aged 6 to 10 years. In total, 77 children participated in the study. Selective and divided attention as well as switching between attentional demands were quantified by the SwAD task. Parents were asked to assess the screen time of their children (TV, smartphone, laptop/PC, game console, tablet). Results show no main or interaction effects of screen time on any of the attention conditions investigated. Based on the present findings, as well as previous studies, we suggest a possible non-linear relationship between the amount of screen time and attention function. Furthermore, we emphasize the relevance of considering the socio-economic background of children and a need for longitudinal studies.

Deep convolutional neural network (CNN) has shown their great advantages in the single image deraining task. However, most existing CNN-based single image deraining methods still suffer from residual rain streaks and details lost. In this paper, we propose a deep neural network including the Multi-scale feature extraction module and the channel attention module, which are embed in the feature extraction sub-network and the rain removal sub-network respectively. In the feature extraction sub-network, the Multi-scale feature extraction module is constructed by a Multi-layer Laplacian pyramid, and is then integrated multi-scale feature maps by a feature fusion module. In the rain removal sub-network, the channel attention module, which assigns different weights to the different channels, is introduced for preserving image details. Experimental results on visually and quantitatively comparison demonstrate that the proposed method performs favorably against other state-of-the-art approaches

The article discusses the issue of the sustainable development of the cross-border market for cultural services in a city divided by the state border. The article uses the example of Cieszyn and Český Těšín, a city divided following the decision of the Council of Ambassadors in 1920. The research carried out so far indicates the main constraints in the harmonious functioning of the cross-border market for cultural services in this city, such as: different cultural policies implemented on both sides of the city, language barriers as well as legal and administrative differences. Therefore, the authors undertook research aimed at recognising the role of Euroregional structures in stimulating the sustainable development of this region. On the basis of the analysis of the Cieszyn Silesia Euroregion's documentation and the results of qualitative and quantitative research, the article describes the role of the Euroregion in building a cross-border market for cultural services. Recommendations were also prepared that could constitute the principles of a common cultural policy not only for Cieszyn and Český Těšín, but also for other European cities in the Schengen Area, which, like Cieszyn and Český Těšín, have been divided by a state border.

This review focuses on the evidence for neurotherapeutics for Attention Deficit Hyperactivity Disorder (ADHD). EEG-Neurofeedback has been tested for about 45 years with latest meta-analyses of randomised controlled trials (RCT) showing small/medium effects compared to non-active controls only. Three small studies piloted neurofeedback of frontal activations in ADHD using functional magnetic resonance imaging or near-infrared spectroscopy, finding no superior effects over control conditions. Brain stimulation has been applied to ADHD using mostly repetitive transcranial magnetic and direct current stimulation (rTMS/tDCS). rTMS has shown mostly negative findings on improving cognition or symptoms. Meta-analyses of tDCS studies targeting mostly dorsolateral prefrontal cortex show small effects on cognitive improvements with only two out of three studies showing clinical improvements. Trigeminal nerve stimulation has shown to improve ADHD symptoms with medium effect in one RCT. Modern neurotherapeutics are attractive due to their relative safety and potential neuroplastic effects. However, they need to be thoroughly tested for clinical and cognitive efficacy across settings and beyond core symptoms and for their potential for individualised treatment.

Panchromatic (PAN) images contain abundant spatial information that is useful for earth observation, but always suffer from low-resolution due to the sensor limitation and large-scale view field. The current super-resolution (SR) methods based on traditional attention mechanism have shown remarkable advantages but remain imperfect to reconstruct the edge details of SR images. To address this problem, an improved super-resolution model which involves the self-attention augmented WGAN is designed to dig out the reference information among multiple features for detail enhancement. We use an encoder-decoder network followed by a fully convolutional network (FCN) as the backbone to extract multi-scale features and reconstruct the HR results. To exploit the relevance between multi-layer feature maps, we first integrate a convolutional block attention module (CBAM) into each skip-connection of the encoder-decoder subnet, generating weighted maps to enhance both channel-wise and spatial-wise feature representation automatically. Besides, considering that the HR results and LR inputs are highly similar in structure, yet cannot be fully reflected in traditional attention mechanism, we therefore design a self augmented attention (SAA) module, where the attention weights are produced dynamically via a similarity function between hidden features, this design allows the network to flexibly adjust the fraction relevance among multi-layer features and keep the long-range inter information, which is helpful to preserve details. In addition, the pixel-wise loss is combined with perceptual and gradient loss to achieve comprehensive supervision. Experiments on benchmark datasets demonstrate that the proposed method outperforms other SR methods in terms of both objective evaluation and visual effect.

A 47-year-old physician suddenly noticed a persistent difficulty maintaining attention. He was awake, alert, and oriented. After two hours he developed fever, ageusia, and anosmia. He denied any previous history of psychiatric illness and was hydrated at the time of the subjective attention impairment. On admission, the patient remained oriented. He reported the persistence of attention problems, anosmia, and mild fatigue. The oxygen saturation 99% while he was breathing ambient air. Laboratory tests were unremarkable. A high-resolution computed tomography of the chest was normal. Nasopharyngeal and throat swabs specimens on reverse transcription-polymerase chain reaction analysis tested positive for SARS-CoV2. On illness day 3, the examination was unchanged, but he continued to complain of difficulties to stay focused. Then, he performed an objective attention test. The test demonstrated a moderate attentional impairment. On day 6, the patient reported a subjective worse in his concentration and performed a second test. Although his physical examination remained normal, the attention performance was worse as compared to day 3. Eight hours after worsening of attention impairment, the patient’s oxygen saturation dropped to 94%. From illness days 9 to 14, the patient evolved with clinical improvement. On day 10, a third objective attention test indicated a mild deficit. On day 16, he did not report any other symptom and the attention test was completely normal. Then, the patient returned to work. Neurological symptoms had been previously described in COVID- 19 patients. However, no previous research had investigated early cognitive deficits preceding the traditional symptoms.

This paper is an interdisciplinary study of novel applications of techniques and tools of an area of brain science, known as Synesthesia (involving associations and/or confusion between distinct senses), to area of Computer Science known as Immersive Virtual Reality (VR), that makes the subject’s awareness of physical self be diminished by being surrounded in an engrossing artificial environment. Natural Synesthesia has for the last decade been an important emerging area in brain science but is present in only a small proportion of the population. For example a person with Natural Synesthesia, when viewing a grapheme, may perceive a color additionally to be associated to the grapheme. In contrast, Artificial synesthesia (also known as virtual synesthesia or synthetic synesthesia) has been defined as the sensory joining due a cross-modal mapping device, where information of one sense is accompanied by an induced perception in another sense. In particular, we propose use of a multimodal manner of displaying information in VR to increase and concentrate attention. Artificial Synesthesia to synthetically create induced associations between senses, allowing Artificial Synesthesia to be experienced by anyone using a VR system. The paper describes the enhancement of immersive VR by use of Artificial Synesthesia to improve the system’s performance at steering and directing the attention of the user. We describe techniques for an enhanced immersive VR that displays associations between a variety of senses: between colors and characters, also between colors and sounds, and between sounds and the position of tactile sensations. The sense association provided by Artificial Synesthesia allows the system to better capture the user’s attention and better direct that attention. A major application of our work in VR-induced Artificial Synesthesia is to provide an enhanced methodology for controlling the attention of the subject, and to improve the direction of attention of subjects undergoing guided imagery therapies for pain relief. Other potential high-impact applications include improved immersive VR, more programmable human/computer interfaces and other medical therapies.

In recent years, there has been significant growth in the ubiquity and popularity of three dimensional(3D) point clouds, with an increasing focus on the classification of 3D point clouds. To extract richer features from point clouds, many researchers have turned their attention to various point set regions and channels within irregular point clouds. However, this approach has limited capability in attending to crucial regions of interest in 3D point clouds and may overlook valuable information from neighboring features during feature aggregation. Therefore, this paper proposes a novel 3D point cloud classification method based on global attention and adaptive graph convolution. The method consists of two main branches: the first branch com-putes attention masks for each point, while the second branch employs adaptive graph convolu-tion to extract global features from the point set. It dynamically learns features based on point interactions, generating adaptive kernels to effectively and precisely capture diverse relationships among points from different semantic parts. Experimental results demonstrate that the proposed model achieves 93.8% in overall accuracy and 90.8% in average accuracy on the ModeNet40 dataset.

With the development of remote sensing satellite technology for Earth observation, remote sensing stereo images have been used for three-dimensional reconstruction in various fields, such as urban planning and construction. However, remote sensing images often include noise, occluded regions, weakly textured areas and repeated textures, which can lead to reduced accuracy in stereo matching and affect the quality of the 3D reconstruction results. To reduce the impact of complex scenes in remote sensing images on stereo matching and to ensure both speed and accuracy, we propose a new end-to-end stereo matching network based on convolutional neural networks (CNNs). The proposed stereo matching network can learn features at different scales from the original images and construct cost volumes with varying scales to obtain richer scale information. Additionally, when constructing the cost volume, we introduce negative disparity to adapt to the common occurrence of both negative and nonnegative disparities in remote sensing stereo image pairs. For cost aggregation, we employ a 3D convolution-based encoder-decoder structure that allows the network to adaptively aggregate information. Before feature aggregation, we also introduce an attention module to retain more valuable feature information, enhance feature representation, and obtain a higher-quality disparity map. By training on the publicly available US3D dataset, we obtain the accuracy that 1.115 pixel in end-point error (EPE) and 5.32% in the error pixel ratio (D1) on the test dataset, and the inference speed is 92 ms. Comparing our model with existing state-of-the-art models, we achieve higher accuracy, and the network is beneficial for the three-dimensional reconstruction of remote sensing images.

Cloud detection in remote sensing images is a crucial preprocessing step that efficiently identifies and extracts cloud-covered areas within the images, ensuring the precision and reliability of subsequent analyses and applications. Given the diversity of clouds and the intricacies of the surface, distinguishing the boundaries between thin clouds and the underlying surface is a major challenge in cloud detection. To address these challenges, an advanced cloud detection method, CloudformerV3, is presented in this paper. The proposed method employs a multi-scale adapter to incorporate dark and bright channel prior information into the model's backbone, enhancing the model's ability to capture prior information and multi-scale details from remote sensing images. Additionally, multi-level large window attention is utilized, enabling high-resolution feature maps and low-resolution feature maps to mutually focus and subsequently merge during the resolution recovery phase. This facilitates the establishment of connections between different levels of feature maps and offers comprehensive contextual information for the model's decoder. Experimental results on the GF1_WHU dataset demonstrate that the method introduced in this paper exhibits superior detection accuracy when compared to state-of-the-art cloud detection models. Furthermore, enhanced detection performance is achieved along cloud edges and with respect to thin clouds, showcasing the efficacy of the proposed method.

With the advancement of technology, signal modulation types are becoming increasingly diverse and complex. The phenomenon of signal time-frequency overlap during transmission poses significant challenges for the classification and recognition of mixed signals, including poor recognition capabilities and low generality. This paper presents a recognition model for fine-grained analysis of mixed signal characteristics, proposing a Geometry Coordinate attention mechanism and introducing a low-rank bilinear pooling module to more effectively extract signal features for classification. The model employs a residual neural network as its backbone architecture and utilizes the Geometry Coordinate attention mechanism for time-frequency weighted analysis based on information geometry theory. This analysis targets multiple-scale features within the architecture, producing time-frequency weighted features of the signal. These weighted features are further analyzed through a low-rank bilinear pooling module, combined with the backbone features, to achieve fine-grained feature fusion. This results in a fused feature vector for mixed signal classification. Experiments were conducted on a simulated dataset comprising 39,600 mixed signal time-frequency plots. The model was benchmarked against a baseline using a residual neural network. The experimental outcomes demonstrated an improvement of 9% in the exact match ratio and 5% in the Hamming score. These results indicate that the proposed model significantly enhances the recognition capability and generalizability of mixed signal classification.

To address the problems of insufficient semantic fusion between text and questions and the lack of consideration of global semantic information encountered in machine reading comprehension models, we proposed a machine reading comprehension model called BERT_hybrid based on BERT and hybrid attention mechanism. In this model, BERT is utilized to separately map the text and questions into the feature space. Through the integration of Bi-LSTM, attention mechanism, and self-attention mechanism, the proposed model achieves comprehensive semantic fusion between text and questions. The probabilities distribution of answers is computed using Softmax. Experimental results on the public dataset DuReader demonstrate that the proposed model achieves improvements in BLEU-4 and ROUGE-L scores compared to existing models. Furthermore, to validate the effectiveness of the proposed model design, we analyze the factors influencing the model’s performance.

With the development of deep learning, the Super-Resolution (SR) reconstruction of microscopic images has improved significantly. However, the scarcity of microscopic images for training, the underutilization of hierarchical features in original Low Resolution (LR) images, and the high-frequency noise unrelated with the image structure generated during reconstruction process are still challenges in the Single Image Super-Resolution (SISR) field. Faced with these issues, we first collected sufficient microscopic images through Motic, a company engaged in the design and production of optical and digital microscopes, to establish a dataset. Secondly, we proposed a Residual Dense Attention Generative Adversarial Network (RDAGAN). The network comprises a generator, an image discriminator, and a feature discriminator. The generator includes a Residual Dense Block (RDB) and a Convolutional Block Attention Module (CBAM), focusing on extracting the hierarchical features of the original LR image. Simultaneously, the added feature discriminator enables the network to generate high-frequency features pertinent to the image’s structure. Finally, we conducted experimental analysis and compared our model with six classic models. Compared with the best model, our model improved PSNR and SSIM by about 1.5dB and 0.2, respectively.

Speech Emotion Recognition (SER) is an interesting and difficult problem to handle. In this paper, we deal with it through the implementation of deep learning networks. We have designed and implemented six different deep learning networks, a Deep Belief Network (DBN), a simple deep neural network (SDNN), a LSTM network (LSTM), a LSTM network with the addition of an attention mechanism (LSTM-ATN), a Convolutional neural network (CNN), and a Convolutional neural network with the addition of an attention mechanism (CNN-ATN), having in mind, apart from solving the SER problem, to test the impact of attention mechanism to the results. Dropout and Batch Normalization techniques are also used to improve the generalization ability (prevention of overfitting) of the models as well as to speed up the training process. The Surrey Audio-Visual Expressed Emotion database (SAVEE), and the Ryerson Audio-Visual Database (RAVDESS) database were used for training and evaluation of our models. The results showed that networks with the addition of the attention mechanism did better than the others. Furthermore, they showed that CNN-ATN was the best among tested networks, achieving an accuracy of 74% for the SAVEE and 77% for the RAVDESS dataset, and exceeded existing state-of-the-art systems for the same datasets.

Attention Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder that affects attention and behavioral control, characterized by constant presence of inattention and hyperactivity. This article describes a study that used a database with results from tests of voluntary and automatic attentional orientation activity in a complex network of ADHD patients, in order to understand the characteristics of the elements and attentional variability of patients. Centrality metrics and the Louvain method were applied to obtain the network communities. The most important elements of the network were identified and differences in reaction times of the activities were observed in the identified communities. The study provides useful information to understand of deficit hyperactivity disorder spectrum in patients with ADHD.

Cerebrovascular and airway structures are tubular structures used for transporting blood and gases, respectively, providing essential support for the normal activities of the human body. Accurately segmenting these tubular structures is the basis of morphology research and patho-logical detection. Nevertheless, accurately segmenting these structures from images presents great challenges due to their complex morphological and topological characteristics. To address this challenge, this paper proposes a framework UARAI based on the U-Net multi-scale reverse at-tention network and sparse convolution network. The framework utilizes a multi-scale structure to effectively extract the global and deep detail features of vessels and airways. Further, it enhances the extraction ability of fine-edge features by a joint reverse attention module. In addition, the sparse convolution structure is introduced to improve the features' expression ability without increasing the model's complexity. Finally, the proposed training sample cropping strategy re-duces the influence of block boundaries on the accuracy of tubular structure segmentation. The experimental findings demonstrate that the UARAI-based metrics, namely Dice and IoU, achieve impressive scores of 90.31% and 82.33% for cerebrovascular segmentation and 93.34% and 87.51% for airway segmentation, respectively. Compared to commonly employed segmentation tech-niques, the proposed method exhibits remarkable accuracy and robustness in delineating tubular structures such as cerebrovascular and airway. These results hold significant promise in facilitating medical image analysis and clinical diagnosis, offering invaluable support to healthcare profes-sionals.

Attention deficit hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder that can diminish the quality of life of both children and adults in academic, occupational, and social contexts. The kynurenine pathway (KP) contains a set of enzymatic reactions involved in tryptophan (TRP) degradation. It is known to be associated with the risk of developing ADHD. This review will address the KP and underlying mechanism of inflammation in ADHD. Potential inflammatory biomarkers reported in the most recent studies are summarized. Although a strong neuroimmunological basis has been established due to advances of recent neurobiological research, the pathophysiology of ADHD remains unclear.

The detection accuracy of bridge superficial defect using the deep neural network approach decreases significantly under light variation and weak texture condition. To address these issues, an enhanced intelligent detection method based on the YOLOv8 deep neural network is proposed in this study. Firstly, multi-branch coordinate attention (MBCA) is proposed to improve the accuracy of coordinate positioning by introducing a global perception module in coordinate attention mechanism. Furthermore, a deformable convolution based on MBCA is developed to improve the adaptability for complex feature shapes. Lastly, the deformable convolutional network-attention-YOLO (DAC-YOLO) detection algorithm is formed by replacing the deep C2F structure in the YOLOv8 architecture with deformable convolution. A supervised dataset consisting of 4794 bridge surface damage images is employed to verify the proposed method, and results show that it achieves improvements of 2.0% and 3.4% in mAP and R. Meanwhile, the model complexity decreases by 1.2G, increasing the detection speed by 3.5/f·s-1.

IIt is important that Master’s Degree students in psychology, regardless of their future specialisa-tion, know about Attention Deficit Hyperactivity Disorder (ADHD). The aim is evaluate and an-alyse the ADHD-related knowledge held by students of Early Childhood Education and Primary Education. The findings that were obtained in this study (on the chronicity of the disorder, changes in manifestations throughout the life cycle, and the importance of early and multidisci-plinary intervention) have clear implications in relation to the specific training in ADHD for fu-ture teachers. It is essential to broaden the specific training in relation to ADHD in studies for the Master’s Degrees in Early Childhood Education and Primary Education and through contin-uous training.

Color can direct visual attention to specific locations through bottom-up and top-down mechanisms. Using Continuous Flash Suppression (CFS) as way to investigate the factors that gate access to consciousness, the current study investigated whether color also directly affected the timing of conscious perception. Low or high spatial frequency (SF) gratings with different orientations were shown as targets to the non-dominant eye of human participants. CFS patterns were presented at a rate of 10Hz to the dominant eye to delay conscious perception of the targets, and participants had the task to report the target’s orientation as soon as they could see it. With low-SF targets, two types of color-based effects became evident. First, when the targets and the CFS patterns had different colors, the targets entered consciousness faster than in trials where the targets and CFS patterns had the same color. Second, when participants searched for a specific target color, targets that matched these search settings entered consciousness faster compared to conditions where the target color was irrelevant and could vary from trial to trial. Thus, the current study demonstrates that color is a central feature of human perception and leads to faster conscious perception of visual stimuli through bottom-up and top-down attentional mechanisms.

Loss of function of the hippocampus or frontal cortex is associated with reduced performance on memory tasks in which subjects are incidentally exposed to cues at specific places in the environment and are subsequently asked to recollect the location at which the cue was experienced. Here, we examined the roles of the rodent hippocampus and frontal cortex in cue-directed attention during encoding of memory for the location of a single incidentally experienced cue. During a spatial sensory preconditioning task, rats explored an elevated platform while an auditory cue was incidentally presented at one corner. The opposite corner acted as an unpaired control location. The rats demonstrated recollection of location by avoiding the paired corner after the auditory cue was in turn paired with shock. Damage to either the dorsal hippocampus or the frontal cortex impaired this memory ability. However, we also found that hippocampal lesions enhanced attention directed towards the cue during the encoding phase while frontal cortical lesions reduced cue-directed attention. These results suggest that the deficit in spatial sensory preconditioning caused by frontal cortical damage may be mediated by inattention to the location of cues during the latent encoding phase, while deficits following hippocampal damage must be related to other mechanisms such as generation of neural plasticity.

Real-time object detection remains a pivotal topic in the realm of computer vision. Balancing the accuracy and speed of object detectors poses a formidable challenge for both academic researchers and industry practitioners. While recent transformer-based models have showncase the prowess of the attention mechanism, delivering remarkable performance improvements over CNNs, their computational demands can hinder their effectiveness in real-time detection tasks. In this paper, we elect to use YOLOX as our robust starting point and introduce a series of effective enhancements, culminating in a new high-performance detector named YOLOAX. To further exploit the power of the attention mechanism, we devise multi-dimensional attention-based modules that activate CNNs, emphasizing the most pertinent regions and bolstering the capacity to learn the most informative image representations from feature maps. Moreover, we introduce a novel leading label assignment strategy called STA, along with a groundbreaking loss function named GEIOU Loss, to further refine our detector's performance. We provide extensive ablation studies on the COCO and PASCAL VOC 2012 detection datasets to validate our proposed methods. Remarkably, our YOLOAX is trained solely on the MS-COCO dataset from scratch, without leveraging any prior knowledge, which achieves an impressive 54.2% AP on the COCO 2017 test set while maintaining a real-time speed of 72.3 fps, surpassing YOLOX by a significant margin of 3.0% AP. Our source code and pre-trained models are openly accessible at https://github.com/KejianXu/yoloax.

Abstract: The promotion and development of healthy cities are vital for enhancing human habitats and fostering sustainable economic growth. Based on the core database of Web of Science and the knowledge graph software, this paper makes a quantitative analysis of the literature related to attention recovery abroad. It is found that in recent years, the research on attention recovery has developed rapidly, the number of related literature has been increasing, and the research content presents the characteristics of interdisciplinary integration. By further analyzing the characteristics of research literature, research context, and knowledge basis, this paper summarizes the empirical research based on the existing quantitative analysis, reviews the research field based on the mechanism of attention recovery, and analyzes the development process and trend based on the research basis of attention recovery. Due to the change of modern life style, human health problems are becoming more and more prominent. Attention restoration design provides a new research idea and method to balance the relationship between humans and the urban environment.

The study focuses on the crucial aspect of lossless compression for FAST pulsar search data. The deep generative model PixelCNN, stacking multiple masked convolutional layers, achieves neural network autoregressive modeling, making it one of the most excellent image density estimators. However, the local nature of convolutional networks causes PixelCNN to concentrate only on nearby information, neglecting important information at greater distances. Although deepening the network can broaden the receptive field, excessive depth can compromise model stability, leading to issues like gradient degradation. To address these challenges, the study combines causal attention modules with residual connections, proposing the Causal Residual Attention Module to enhance the PixelCNN model. This innovation not only resolves convergence problems arising from network deepening but also widens the receptive field. It effectively utilizes global features, particularly capturing vertically correlated features prominently present in subgraphs of candidates. This significantly enhances its capability to model pulsar data.In the experiments, the model is trained and validated using the HTRU1 dataset. The study compares the average negative log-likelihood score with baseline models like GMM, STM, and PixelCNN. The results demonstrate the superior performance of the our model over other models. Finally, the study introduces the practical compression encoding process by combining the proposed model with arithmetic coding.

This paper proposes a multimodal fusion 3D target detection algorithm based on the attention mechanism to improve the performance of 3D target detection. The algorithm utilizes point cloud data and information from camera. For image feature extraction, the ResNet50+FPN architecture extracts features at four levels. Point cloud feature extraction employs the voxel method and FCN to extract point and voxel features. The fusion of image and point cloud features is achieved through regional point fusion and regional voxel fusion methods. After information fusion, the Coordinate attention mechanism and SimAM attention mechanism extract fusion features at a deep level. The algorithm's performance is evaluated using the DAIR-V2X dataset. The results show that compared to the Part-A2 algorithm, the proposed algorithm improves the mAP value by 7.9% in BEV view and 7.8% in 3D view at IOU=0.5 (cars) and IOU=0.25 (pedestrians and cyclist). At IOU=0.7 (cars) and IOU=0.5 (pedestrians and cyclist), the mAP value of the SECOND algorithm is improved by 5.4% in the BEV view and 4.3% in the 3D view, compared to other comparison algorithms.

3D point cloud classification tasks have been a hot topic in recent years. Most existing point cloud processing frameworks lack context-aware features due to the deficiency of sufficient local feature extraction information. Therefore, we design an augmented sampling and grouping (ASG) module to efficiently obtain fine-grained features from the original point cloud. In particular, this method strengthens the domain near each centroid and makes reasonable use of the local mean and global standard deviation to mine point cloud’s local and global features. In addition to this, inspired by the transformer structure UFO-ViT in 2D vision tasks, we first try to use a linearly-normalized attention mechanism in point cloud processing tasks, investigating a novel transformer-based point cloud classification architecture UFO-Net. An effective local feature learning module is adopted as a bridging technique to connect different feature extraction modules. Importantly, UFO-Net employs multiple stacked blocks to better capture feature representation of the point cloud. Extensive ablation experiments on public datasets show that our method outperforms other state-of-the-art methods. For instance, our network performed with 93.7% overall accuracy on the ModelNet40 dataset, which was 0.5% higher than PCT. Our network also archived 83.8% overall accuracy on the ScanObjectNN dataset, which is 3.8% better than PCT.

Speech emotion recognition is a critical component for achieving natural human-robot interaction. The modulation-filtered cochleagram is a feature based on auditory modulation perception, which contains multi-dimensional spectral-temporal modulation representation. In this study, we propose an emotion recognition framework that utilizes a multi-level attention network to recognize emotions from the modulation-filtered cochleagram. The channel-level attention and spatial-level attention modules are used to capture emotional saliency maps of channel and spatial feature representations from the 3D convolution feature maps, respectively. Furthermore, the temporal-level attention module captures significant emotional regions from the concatenated feature sequence of the emotional saliency maps. Our experiments on the IEMOCAP dataset demonstrate that the modulation-filtered cochleagram significantly improves the prediction performance of categorical emotion compared to other evaluated features. Moreover, our emotion recognition framework achieves a better unweighted accuracy of 71% in categorical emotion recognition than several existing approaches in the experiments. In summary, our study demonstrates the effectiveness of the modulation-filtered cochleagram in speech emotion recognition, and our proposed multi-level attention framework provides a promising direction for future research in this field.

Culture exploits the acquisition of meaningful content by crafting regimes of shared attention, determining what is relevant, valuable, and salient. Culture changes the field of relevant social affordances worthy of being acted upon in a context-sensitive manner. When relevant affordances are highly weighted, their attentional capture and their salience increase the probability of them being enacted due to the associated expectation for minimizing prediction error. This process is known as active inference. In the digital era, individuals need to infer the action-related attributes of digital cues, here characterized as digital affordances. The digital affordances of digital social platforms are of particular interest here. Digital social affordances are defined as online possibilities of social interactions. By their own nature, these are salient because they are related to social interactions and relevant social cues. However, the problem of digital social platforms is that they are not equivalent to situated social interactions because their structure is built, mediated, and defined by third-parties with diverse interests. The third-parties behind the digital social platforms are using the same mechanism exploited by culture to manipulate the shared patterns of attention. Moreover, digital social platforms are deliberately designed to be hyper-stimulating, making digital social affordances highly rewarding and increasingly salient. This appropriation, for economic purposes, is an issue of great importance, especially as the COVID-19 pandemic brought deep global changes, pushing societies to an online digital way of life. Here, we examined different types of digital social affordances under an active inference view, placing them into two categories, those for self-identity formation, and those for belief-updating. This paper aims to analyze digital social affordances in light of the prediction error dynamics they might elicit to their users. Although each of the analyzed digital social affordances allows different epistemic and instrumental digital actions, they all share the characteristic of having an "easy" and a fast expected rate of error reduction. Here, we aim to provide a new hypothesis about how the design behind digital social affordances is built on our natural attractiveness to minimize prediction error and the resulting positive embodied feelings when doing so. Finally, it is suggested that because digital social affordances are becoming highly weighted in the field of affordances, this might be putting at risk our context-sensitive grip on a rich, dynamic and varied field of relevant affordances.

The object detection task is usually affected by complex backgrounds. In this paper, a new image object detection method is proposed, which can perform multi-feature selection on multi-scale feature maps. By this method, a bidirectional multi-scale feature fusion network is designed to fuse semantic features and shallow features to improve the detection effect of small objects in complex backgrounds. When the shallow features are transferred to the top layer, a bottom-up path is added to reduce the number of network layers experienced by the feature fusion network, reducing the loss of shallow features. In addition, a multi-feature selection module based on the attention mechanism is used to minimize the interference of useless information on subsequent classification and regression, allowing the network to adaptively focus on appropriate information for classification or regression to improve detection accuracy. Because the traditional five-parameter regression method has severe boundary problems when predicting objects with large aspect ratios, the proposed network treats angle prediction as a classification task. The experimental results on the DOTA dataset, the self-made DOTA-GF dataset and the HRSC 2016 dataset show that, compared with several popular object detection algorithms, the proposed method has certain advantages in detection accuracy.

Few-shot classification is challenging since the goal is to classify unlabeled samples with very few labeled samples provided. It has been shown that cross attention helps generate more discriminative features for few-shot learning. This paper extends the idea and proposes two cross attention modules, namely the cross scaled attention (CSA) and the cross aligned attention (CAA). Specifically, CSA scales different feature maps to make them better matched, and CAA adopts the principal component analysis to further align features from different images. Experiments showed that both CSA and CAA achieve consistent improvements over state-of-the-art methods on four widely used few-shot classification benchmark datasets, miniImageNet, tieredImageNet, CIFAR-FS, and CUB-200-2011, while CSA is slightly faster and CAA achieves higher accuracies.

Compressed Sensing (CS) MRI has shown great potential in enhancing time efficiency. Deep learning techniques, specifically Generative Adversarial Networks (GANs), have emerged as potent tools for speedy CS-MRI reconstruction. Yet, as the complexity of deep learning recon-struction models increases, this can lead to prolonged reconstruction time and challenges in achieving convergence. In this study we present a novel GAN-based model that delivers superior performance without escalating model complexity. Our generator module, built on the U-net architecture, incorporates dilated residual (DR) networks, thus expanding the network's receptive field without increasing parameters or computational load. At every step of the downsampling path, this revamped generator module includes a DR network, with the dilation rates adjusted according to the depth of the network layer. Moreover, we have introduced a channel attention mechanism (CAM) to distinguish between channels and reduce background noise, thereby fo-cusing on key information. This mechanism adeptly combines global maximum and average pooling approaches to refine channel attention. We conducted comprehensive experiments with the designed model using public domain MRI datasets of the human brain. Ablation studies af-firmed the efficacy of the modified modules within the network. Compared to other relevant models, our proposed model exhibits exceptional performance, achieving not only excellent sta-bility but also outperforming other networks in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The model presents a promising pathway for enhancing the efficiency and quality of CS-MRI reconstruction.

Simulated (sim) racing is an emerging esport that has garnered much interest in recent years and has been a relatively under-researched field in terms of expertise and performance. When examining expertise, visual attention has been of particular interest to researchers, with eye tracking technology commonly used to assess visual attention. In this study, we examined the visual attention allocation of high and low skilled sim racers during a time trial task using Tobii 3 glasses. Participants were allocated to either group according to their fastest lap times. Our results indicate that when eye tracking metrics were normalised to lap time, there was no difference in the relative length of attention allocation (fixation behaviour), although lower skilled racers did have significantly greater fixation counts and durations across laps overall. Interestingly, high and low skilled sim racers differed in where they allocated their attention during the task, with high skilled sim racers allocating significantly less attention to the track relative to other areas of the display. This would allow higher skilled racers to obtain relatively more information from heads-up display elements in-game, all whilst driving at faster speeds. This study provides evidence that high and low skilled sim racers show similar lap time-corrected fixation behaviour, but how they allocate attention while driving differs.

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research towards the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we introduce a set of metrics considering both quantitative and qualitative aspects of the road network. Compared to traditional neural networks, our HAN model demonstrates superior accuracy and F1-score, particularly for road types with comparable samples. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation.

Accurate estimation of Remaining Useful Life (RUL) for aircraft engines is essential for ensuring safety and uninterrupted operations in the aviation industry. Numerous investigations have leveraged the success of attention-based Transformer architecture in sequence modeling tasks, particularly in its application to RUL prediction. These studies primarily focus on utilizing onboard sensor readings as input predictors. While various Transformer-based approaches have demonstrated improvement in RUL predictions, their exclusive focus on temporal attention within multivariate time series sensor readings, without considering sensor-wise attention, raises concerns about potential inaccuracies in RUL predictions. To address this concern, our paper proposes a novel solution in the form of a two-stage attention based hierarchical transformer (STAR) frame-work. This approach incorporates a two-stage attention mechanism, systematically addressing both temporal and sensor-wise attentions. Furthermore, we enhance the STAR RUL prediction framework by integrate hierarchical encoder-decoder structures to capture valuable information across different time scales. By conducting extensive numerical experiments with the CMAPSS datasets, we demonstrate that our proposed STAR framework significantly outperforms current state-of-the-art models for RUL prediction.

People are drawn to woodcut-style designs due to their striking visual impact and strong contrast. However, traditional woodcut prints and previous computer-aided methods have not addressed the issues of dwindling design inspiration, lengthy production times, and complex adjustment procedures. We propose a novel network framework, the Woodcut-style Design Assistant Network (WDANet), to tackle these challenges. Notably, our research is the first to utilize diffusion models to streamline the woodcut-style design process. We've curated the Woodcut-62 dataset, featuring works from 62 renowned historical artists, to train WDANet in absorbing and learning the aesthetic nuances of woodcut prints, offering users a wealth of design references. Based on a noise reduction network, our dual cross-attention mechanism effectively integrates text and woodcut-style image features. This allows users to input or slightly modify a text description to quickly generate accurate, high-quality woodcut-style designs, saving time and offering flexibility. As confirmed by user studies, quantitative and qualitative analyses show that WDANet outperforms the current state-of-the-art in generating woodcut-style images and proves its value as a design aid.

Underwater image processing faces significant challenges due to the absorption and scattering of light as it travels through water. A self-supervised learning network based on the self-attention mechanism is proposed for underwater visual applications in this paper. The goal is to improve the effectiveness and stability of feature extraction from underwater images. By incorporating self-attention mechanism, the sensitivity of the original network architecture to degraded features of blurred underwater images is enhanced. The network proposed in this paper is trained using transfer learning and evaluated on various underwater image datasets. With distributive, quantitative, and qualitative advantages compared with other methods, experimental results have demonstrated that the algorithm presented shows a slighter decline in feature extraction ability for blurred images as the turbidity of water increases.

Vehicle re-identification research under surveillance cameras has yielded impressive results. However, the challenge of Unmanned Aerial Vehicle (UAV)-based vehicle re-identification (ReID) presents a high degree of flexibility, mainly due to complicated shooting angles, occlusions, low discrimination of top-down features, and significant changes in vehicle scales. To address this, we propose a novel Dual Mixing Attention Network (DMANet) to extract discriminative features robust to variations in viewpoint. Specifically, we first present a plug-and-play Dual Mixing Attention Module (DMAM) to capture pixel-level pairwise relationships and channel dependencies, where DMAM is composed of Spatial Mixing Attention (SMA) and Channel Mixing Attention (CMA). First, the original feature is divided according to the dimensions of spatial and channel to obtain multiple subspaces. Then, a learnable weight is applied to capture the dependencies between local features in the mixture space. Finally, the features extracted from all subspaces are aggregated to promote their comprehensive feature interaction. Moreover, the DMAM can be readily inserted into backbone networks at any depth to improve vehicle discrimination. The experiments show that the proposed structure gains a better performance compared with the representative methods in the UAV-based vehicle ReID task. Our code and models will be publicly released.

With the rise of the Internet of Things (IOT), mobile devices and Location-Based Social Network (LBSN), an abundant amount of trajectory data has made research on location prediction more popular. The check-in data shared through LBSN hides information related to life patterns, obtaining this information is helpful for location prediction. However, the trajectory data recorded by mobile devices is different from check-in data that has semantic information. In order to obtain the user’s semantic, relevant studies match the stay point to the nearest Point of Interest (POI), but location error may lead to wrong semantic matching. Therefore, we propose A Self-Attention for Next Location Prediction based on Semantic Mining to predict the next location. When calculating the semantic feature of a stay point, the first step is to search for the k nearest POI, then use the reciprocal of the distance from the stay point to the k nearest POI and the number of categories as weights. Finally, we use the probability to express semantic without losing other important semantic information. Furthermore, this research combined with sequential pattern mining can bring richer semantic features. In order to better perceive the trajectory, temporal features learn periodicity of time series by sine function. In terms of location features, we build a directed weighted graph and regard the frequency of users visiting locations as the weight, so the location features are rich in contextual information. We then adopt the Self-Attention model to capture long-term dependencies in long trajectory sequences. Experiments in Geolife show that the semantic matching of this study improved by 45.78% in TOP@1 compared with the closest distance search for POI. Compared with the baseline, the model proposed in this study improved by 2.5% in TOP@1.

Several commerical quantum computers are now available that offer Hybrid Classical-Quantum computing. Application is made to a classical-quantum model of human neocortex, Statistical Mechanics of Neocortical Interactions (SMNI), which has had its applications published in many papers since 1981. However, this project only uses Classical (super-)computers. Since 2015, PATHINT, has been used as a numerical algorithm for folding path-integrals. Applications in several systems in several disciplines has generalized been from 1 dimension to N dimensions, and from classical to quantum systems, qPATHINT. Papers have applied qPATHINT to neocortical interactions and financial options. The classical space described by SMNI applies nonlinear nonequilibrium multivariate statistical mechanics to synaptic neuronal interactions, while the quantum space described by qPATHINT applies synaptic contributions from Ca2+ waves generated by astrocytes at tripartite neuron-astrocyte-neuron sites. Previous SMNI publications since 2013 have calculated the astrocyte Ca2+ wave synaptic interactions from a closed-form (analytic) expression derived by the author. However, more realistic random shocks to the Ca2+ waves from ions entering and leaving these wave packets should be included using qPATHINT between electroencephalographic (EEG) measurements which decohere the quantum wave packets. This current project extends calculations to multiple scales of interaction between classical events and expectations over the Ca2+ quantum processes to include these random shocks to fit EEG data to the SMNI model, with previous analytic forms for the quantum processes replaced by qPATHINT. The classical-quantum system is fit using the author's Adaptive Simulated Annealing (ASA) importance-sampling optimization code. Gaussian Quadratures are used for numerical calculation of momenta expectations of the astrocyte processes that contribute to SMNI synaptic interactions. This project demonstrates how some hybrid classical-quantum systems may be calculated using only classical (super-)computers. Recent calculations also are reported using the closed-form expression, with and without shocks.

Sarcasm is a linguistic expression often used to communicate the opposite of what is said, usually something that is very unpleasant with an intention to insult or ridicule. Inherent ambiguity in sarcastic expressions, make sarcasm detection very difficult. In this work, we focus on detecting sarcasm in textual conversations from various social networking platforms and online media. To this end, we develop an interpretable deep learning model using multi-head self-attention and gated recurrent units. Multi-head self-attention module aids in identifying crucial sarcastic cue-words from the input, and the recurrent units learn long-range dependencies between these cue-words to better classify the input text. We show the effectiveness of our approach by achieving state-of-the-art results on multiple datasets from social networking platforms and online media. Models trained using our proposed approach are easily interpretable and enable identifying sarcastic cues in the input text which contribute to the final classification score. We visualize the learned attention weights on few sample input texts to showcase the effectiveness and interpretability of our model.

In this paper we address the understanding of the problem, of why a deep learning model decides that an individual is eligible for a loan or not. Here we propose a novel approach for inferring, which attributes matter the most, for making a decision in each specific individual case. Specifically we leverage concepts from neural attention to devise a novel feature wise attention mechanism. As we show, using real world datasets, our approach offers unique insights into the importance of various features, by producing a decision explanation for each specific loan case. At the same time, we observe that our novel mechanism, generates decisions which are much closer to the decisions generated by human experts, compared to the existent competitors.

In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.

Visual question answering (VQA) is receiving increasing attention from researchers in both the computer vision and natural language processing fields. There are two key components in the VQA task: feature extraction and multi-modal fusion. For feature extraction, we introduce a novel co-attention scheme by combining Sentence-guide Word Attention (SWA) and Question-guide Image Attention (QIA) in a unified framework. To be specific, the textual attention SWA relies on the semantics of the whole question sentence to calculate contributions of different question words for text representation. For the multi-modal fusion, we propose a “Cross-modal Multistep Fusion (CMF)” network to generate multistep features and achieve multiple interactions for two modalities, rather than focusing on modeling complex interactions between two modals like most current feature fusion methods. To avoid the linear increase of the computational cost, we share the parameters for each step in the CMF. Extensive experiments demonstrate that the proposed method can achieve competitive or better performance than the state-of-the-art.

Recently, attention mechanisms have developed into an important tool for performance improvement of deep neural networks. In computer vision, attention mechanisms are generally divided into two main branches: spatial and channel attention. Both attention categories have their own advantages. The fusion of both attentions achieves higher performance, on the cost of the computational load. This paper introduces an innovative and lighter n-shifted sigmoid channel and spatial attention (CSA) module to reduce the computational cost and to improve the 3D scene relevant features selection. To validate the proposed attention module, 3D scene object detection in the deep Hough voting point sets is considered as the testing application. The proposed attention module with its piecewise n-shifted sigmoid activation function improves the network’s learning and generalization capacity which effectively predict bounding box parameters directly from 3D scenes and detect objects more accurately. This advantage is achieved by selectively attending to more relevant features of the input data. When used in the deep Hough voting point sets, the proposed attention module outperforms state-of-the-art 3D detection methods on the sizable SUNRGBD dataset. Experiments conducted showed an increase of 12.02 mean accuracy precision (mAP) when compared to the celebrated VoteNet (without attention). It also got 9.92 mAP higher compared to the MLVCNet, and 10.32 mAP higher than the Point Transformer. The proposed model not only decreases the sigmoid vanishing gradient problem but also brings out valuable features by fusing channel-wise and spatial information while improving accuracy results in 3D object detection.

Human activities and natural events alter the earth’s surface and pose a constant threat to the environment. Thus, accurately monitoring and predicting these changes in a timely manner is crucial to provide solutions and mitigate the environmental consequences beforehand. This research introduces a novel framework, called HCD-Net, for change detection using bi-temporal hyperspectral images. The framework is based on double-stream deep feature extraction and an attention mechanism. The first stream focuses on deep feature extraction through 3D convolution layers and 3D Squeeze-and-Excitation (SE) blocks. The second stream focuses on deep feature extraction through 2D convolution and 2D SE blocks. The extracted deep features are then concatenated and fed to dense layers for decision-making. The efficiency of HCD-Net is compared to the state-of-the-art change detection methods. Additionally, the bi-temporal Airborne Visible InfraRed Imaging Spectrometer (AVIRIS) hyperspectral dataset was used for further evaluation of the change detection results. The results show that HCD-Net has a higher accuracy and the lowest false alarm rate, where the overall classification accuracy is above 96%, and the kappa coefficient is over 0.9.

Skin cancer is a global health concern with increasing prevalence, necessitating effective early detection and classification systems. Transfer learning has emerged as a powerful tool in this domain, enhancing diagnostic accuracy. Attention mechanisms, which selectively focus on pertinent image features, play a pivotal role in transfer learning. While previous studies have highlighted their effectiveness, their applicability across different models and datasets remains understudied. This empirical study explores the impact of various attention mechanisms on the performance of transfer learning models for skin cancer detection and classification. Using five transfer learning models (DenseNet121, InceptionV3, MobileNet, VGG16, and Xception) and six attention mechanisms (Channel Attention, Global Context Attention, Guided Attention, Nonlocal Attention, Positional Attention, and Spatial Attention), we conducted 105 experiments across three datasets. Traditional metrics (accuracy, precision, recall, and f1-score) were employed for empirical validation. The results reveal a nuanced relationship between attention mechanisms, transfer learning models, and datasets. Overall, attention mechanisms exhibit the potential to enhance skin cancer classification. Spatial and channel attention mechanisms consistently outperform others, offering simplicity and effectiveness. Model-specific selection of attention mechanisms is crucial, with a trade-off between model complexity and performance evident. This study provides insights into developing efficient skin cancer classification models utilizing attention mechanisms.

Machinery degradation assessment can offer meaningful prognosis and health management in-formation. Although numerous machine prediction models based on artificial intelligence have emerged in recent years, they still face a series of challenges: (1) Many models continue to rely on manual feature extraction. (2) Deep learning models still struggle with long sequence prediction tasks. (3) Health indicators are inefficient for remaining useful life (RUL) prediction with cross-operational environments when dealing with high-dimensional datasets as inputs. This research proposes a health indicator construction methodology based on a transformer self-attention transfer network (TSTN). This methodology can directly deal with the high-dimensional raw dataset and keep all the information without missing when the signals are taken as the input of the diagnosis and prognosis model. First, we design an encoder with a long-term and short-term self-attention mechanism to capture crucial time-varying information from a high-dimensional dataset. Second, we propose an estimator that can map the embedding from the encoder output to the estimated degradation trends. Then, we present a domain dis-criminator to extract invariant features from different machine operating conditions. The case studies with the FEMTO-ST bearing dataset and the Monte Carlo method for RUL prediction during the degradation process are conducted. The experiment results fully exhibited the signif-icant advantages of the proposed method compared to other state-of-the-art techniques.

The current neural networks for tomato leaf disease recognition have problems such as large model parameters, long training time, and low model accuracy. To solve these problems, a lightweight convolutional neural network LBFNet is proposed in this paper.First, a lightweight convolutional neural network LBFNet is established as the base model. Secondly, a three-channel attention mechanism module is introduced to learn the disease features in tomato leaf disease images and reduce the interference of redundant features. Finally, a cascade module is introduced to increase the depth of the model, solve the gradient descent problem, and reduce the loss caused by increasing the depth of the model. The quantized pruning technique is also used to further compress the model parameters and optimize the model performance. The results show that the LBFNet model achieves 99.06% accuracy on the LBFtomato dataset, with a training time of 996s and a single classification accuracy of over 94%. Further training using the saved weight file after quantized pruning makes the model accuracy reach 97.66%. Compared with the base model, the model accuracy was improved by 28%, and the model parameters were reduced by 96.7% compared with the traditional Resnet50. It was found that LBFNet can quickly and accurately identify tomato leaf diseases in complex environments, providing effective assistance to agricultural producers.

Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder. Given the growing evidence of gut microbiota being involved in psychiatric (including neurodevelopmental) disorders, we aimed to identify differences in gut microbiota composition between participants with ADHD and controls and to investigate the role of the microbiota in inattention and hyperactivity/impulsivity. Fecal samples were collected from 107 participants (NADHD=42; Ncontrols=50; NsubthreholdADHD=15; range age: 13-29 years). The relative quantification of bacterial taxa was done using 16S ribosomal RNA gene amplicon sequencing. Beta-diversity revealed significant differences in bacterial composition between participants with ADHD and healthy controls, which was also significant for inattention, but showing a trend in case of hyperactivity/impulsivity only. Ten genera showed nominal differences (P < 0.05) between both groups, of which seven genera were tested for their association with ADHD symptom scores (adjusting for age, sex, body mass index, time delay between feces collection and symptoms assessment, medication use and family relatedness). Our results show that variation of a genus from the Ruminococcaceae family (Ruminococcaceae_UCG_004) is associated (after multiple testing correction) with inattention symptoms, and suggest a role of gut microbiota in ADHD pathophysiology.

This review paper explores auditory tactile (AT) synesthesia, a rare neurological condition where sounds evoke tactile sensations. The paper provides a historical overview of the condition and discusses its epidemiology, with a prevalence of less than 1% of the general population. The neurological basis of AT synesthesia is explored, including the role of cross-modal processing and hyperconnectivity within the brain. The paper also describes the phenomenology of the condition, including the range of tactile sensations that can be experienced in response to different sounds. The occurrence of AT synesthesia in the present-day world is discussed, including its relationship to music and art. Various hypotheses surrounding the development and maintenance of AT synesthesia are reviewed, focusing on genetic and environmental factors. The implications for clinical practice are explored, including potential benefits for individuals with sensory processing disorders. Finally, the paper concludes with a discussion of future directions for research in this field, including the need to explore further the underlying neural mechanisms of AT synesthesia and potential therapeutic interventions.

Pedestrian object detection plays a significant role in intelligent systems such as intelligent traffic and monitoring. Traditional machine learning methods on pedestrian detection have shown various drawbacks, \eg{} low accuracy, slow speed, \etc The Convolutional Neural Network (CNN) based object detection algorithms have demonstrated remarkable advantages in the field of pedestrian detection. However, the mainstream CNNs still face the problems of slow speed and low detection accuracy, especially on small and occluded targets from aerial perspective. In this paper, we propose Multi-Scale Attention YOLO (MSA-YOLO) detection algorithm to address the above issues. MSA-YOLO includes a Squeeze, Excitation and Cross Stage Partial (SECSP) channel attention module for CNNs to extract richer pedestrian features with a small number of extra parameters. It also contains a multi-scale prediction module to capture the information among different pedestrian scales, which can recognize the small objects with higher accuracy and significantly reduce the missed detection. To sufficiently evaluate our proposed model, we manually collect and annotate a new benchmark dataset, Luoyang Pedestrian Dataset \footnote{The dataset can be downloaded through this anonymous link: \url{https://drive.google.com/drive/folders/13po1FX7Qk5RDgb60-dzOi74cq_kqDJtM?usp=sharing} }, which has much more sample annotations, features, scenes and image view angles than the existing benchmark datasets. In addition, the images in our dataset have higher resolution than most of benchmark pedestrian detection datasets, which can provide more detailed features of pedestrians and thus improve the model performance. When tested on Luoyang Pedestrian Dataset, our proposed MSA-YOLO algorithm significantly outperform the most commonly used baseline models with almost the same model size. This shows the efficiency of our proposed model. (The code and new dataset will be released to the public later.)

(1) Background: Attention Deficit Hyperactivity Disorder (ADHD) and Developmental Language Disorder (DLD) are neurodevelopmental disorders that affect various areas of chil-dren’s development, such as language. There is an emerging idea that ADHD is characterised by the presence of language difficulties, which could be explained by the high comorbidity between ADHD and DLD. The purpose of this study is to analyse the empirical evidence of language com-petence in children aged 6–17 years old, diagnosed with ADHD and/or DLD. (2) Method: Fifteen studies with experimental designs were identified from Scopus, PsycINFO and WoS databases, reporting on language skills in children diagnosed with ADHD and/or DLD. Studies relating ex-ecutive functioning to language skills in this target population were also included. (3) Results: The literature is heterogeneous and different components of language are also examined. Even though the results are contradictory they convincingly demonstrate that there are overlapping symptoms between ADHD and DLD, such as language skills and executive functions. (4) Conclusions: the differences in the samples limit the generalisability of the results. Therefore, this review highlights the importance of considering language skills when designing individualised interventions for the population with ADHD and DLD, both in comorbidity and in isolation.

Objective: This study investigated the effects of an easily implemented 8-week program centered around jump rope exercise (JRE) on executive function among children with ADHD. Methods: Using the Stroop Color Word Test to assess inhibitory control, the n-back task (1- and 2-back) to assess working memory, and task switching to assess cognitive flexibility. Results: After the intervention, there were within-group effects only for the experimental group, with higher accuracy on the 1-back working memory task (t= -2.79，p= 0.011< 0.05，Cohen’s d= 0.60) and on task switching after compared with before the JRE intervention (t= -4.00，p=0.01<0.05，Cohen’s d= 0.85), but with no change in reaction time. There was no significant within-group difference on the Stroop test (P> 0.05). Additionally, there were no between-group effects as assessed by one-way analyses of variance. Conclusion: 8-week program focused on JRE improved two aspects of executive function, working memory and cognitive flexibility, with no significant effect on a third aspect, inhibitory control, among children with ADHD aged 7 to 12 years.

Mindfulness interventions have been implemented in many countries. This study aimed to examine the psychometric properties of English and Thai-version of the 15-item mindfulness attention awareness scale (MAAS) across five samples. A descriptive correlation research was conducted in the Philippines and Thailand, and five data sets were generated using self-reported and online questionnaires. Exploratory factor analyses were used to explore the factorial structure of the MAAS. Confirmatory factor analyses were performed to test measurement invariance across samples. Concurrent validity was tested by examining relationships between the MAAS and psychological well-being (PWB). A unidimensional structure of the MAAS was documented across the five samples. The MAAS demonstrated measurement invariance across samples for both English and Thai versions. Concurrent validity was displayed through significant correlations with PWB. This study produced evidence to support the construct validity, concurrent validity, and reliability of the English and Thai versions of MAAS. This study was not registered.

Attention Deficit-Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder with high incidence in children and adolescents characterized by motor hyperactivity, impulsivity, and inattention. MRI-based evidences support that neuroanatomical abnormalities as the volume reduction of neocortex and hippocampus are shared by several neuropsychiatric diseases as schizophrenia, autism spectrum disorder and ADHD. In addition, it is well documented the abnormal development and postnatal pruning of dendritic spines of neocortical neurons in schizophrenia, autism spectrum disorder and intellectual disability. A recent report using the prenatal nicotine exposure murine model of ADHD support a delay in spine maturation in CA1 neurons correlated with impaired working memory and hippocampal long-term potentiation (LTP). In vivo spine imaging show that dendritic spines are dynamic structures exhibiting Hebbian and homeostatic plasticity triggering intracellular cascades involving glutamate receptors, calcium influx and remodeling of F-actin network. The LTP-induced insertion of postsynaptic glutamate receptors is associated to the enlargement of spine head and long-term depression (LTD) to the spine shrinkage. In this review, we summarize recent evidence emerged from meta-analysis of brain imaging data from ADHD patients, risk loci from global genome-wide analysis and new reports focused on spine molecular structure and dynamics using in vivo imaging in neocortex and hippocampus.

In recent years, neural networks based on attention mechanisms have been increasingly widely used in speech recognition, separation, enhancement, and other fields. In particular, the convolution-augmented transformer has achieved good performance as it can combine the advantages of convolution and self-attention. Recently, the gated attention unit (GAU) has been proposed. Compared with the traditional multi-head self-attention, approaches with GAU are effective and computationally efficient. In this article, we propose a network for speech enhancement called CGA-MGAN, a kind of Metric GAN based on convolution-augmented gated attention. CGA-MGAN captures local and global correlations in speech signals at the same time through the fusion of convolution and gated attention units. Experiments on Voice Bank + DEMAND show that the CGA-MGAN we propose achieves an excellent performance (3.47 PESQ, 0.96 STOI, and 11.09dB SSNR) at a relatively small model size (1.14M).

Land cover mapping provides spatial information on the physical properties of the Earth’s surface, for various classes of wetlands, artificial surface and constructions, vineyards, water bodies, etc. Having reliable information on land cover is crucial to developing solutions to a variety of environmental problems such as destruction of important wetlands/forests, and loss of fish and wildlife habitats. This has made land cover mapping one of the most widespread application areas in remote sensing computational imaging. However, due to the differences between modalities in terms of resolutions, content, and sensors, integrating complementary information that multi-modal remote sensing imagery exhibits into a robust and accurate system still remains challenging, and classical segmentation approaches generally do not give satisfactory results for land cover mapping. In this paper, we propose a novel dynamic deep network architecture, AMM-FuseNet, that promotes the use of multi-modal remote sensing images for the purpose of land cover mapping. The proposed network exploits the hybrid approach of the Channel Attention mechanism and Densely Connected Atrous Spatial Pyramid Pooling (DenseASPP). In the experimental analysis, in order to to verify the validity of the proposed method, we test AMM-FuseNet applied to four datasets whilst comparing it to the 6 state-of-the-art models of DeepLabV3+, PSPNet, UNet, SegNet, DenseASPP, and DANet. In addition, we also demonstrate the capability of AMM-FuseNet under minimal training supervision (reduced number of training samples) compared to the state-of-the-art, achieving less accuracy loss even for the case with 1/20 of the training samples.

Satellite communication is expected to play a vital role in realizing Internet of Remote Things (IoRT) applications. This article considers an intelligent reflecting surface (IRS)-assisted downlink low Earth orbit (LEO) satellite communication network, where IRS provides additional reflective links to enhance the intended signal power. We aim to maximize the sum-rate of all the terrestrial users by jointly optimizing the satellite’s precoding matrix and IRS’s phase shifts. However, it is difficult to directly acquire the instantaneous channel state information (CSI) and optimal phase shifts of IRS due to the high mobility of LEO and the passive nature of reflective elements. Moreover, most conventional solution algorithms suffer from high computational complexity and are not applicable to these dynamic scenarios. A robust beamforming design based on graph attention networks (RBF-GAT) is proposed to establish a direct mapping from the received pilots and dynamic network topology to the satellite and IRS’s beamforming, which is trained offline using the unsupervised learning approach. The simulation results corroborate that the proposed RBF-GAT can achieve approximate performance compared to the upper bound with low complexity.

For any molecule, network, or process of interest, to keep up with new publications on these, is becoming increasingly difficult. For many cellular processes, molecules and their interactions that need to be considered can be very large. Automated mining of publications can support large scale molecular interaction maps and database curation. Text mining and Natural Language Processing (NLP)-based techniques are finding their applications in mining the biological literature, handling problems such as Named Entity Recognition (NER) and Relationship Extraction (RE). Both rule-based and machine learning (ML)-based NLP approaches have been popular in this context, with multiple research and review articles examining the scope of such models in Biological Literature Mining (BLM). In this review article, we explore self-attention based models, a special type of neural network (NN)-based architectures that have recently revitalized the field of NLP, applied to biological texts. We cover self-attention models operating either at a sentence level or an abstract level, in the context of molecular interaction extraction, published from 2019 onwards. We conduct a comparative study of the models in terms of their architecture. Moreover, we also discuss some limitations in the field of BLM that identifies opportunities for the extraction of molecular interactions from biological text.

The aim of this paper is to use deep learning tools to innovate pre-trained object detection models to improve the accuracy of non-destructive testing (NDT) of civil aviation maintenance. First, this thesis classifies object defects for NDT, such as cracks, undercut, etc. Nowadays, thesis surveys innovation deep-learning methods technology is used to improve the defect detection performance inferencing capability, increase the accuracy and efficiency of automatic identification which in enhanced the safety and reliability of aircraft fuselage in future, mark hidden cracks and solve the challenges that cannot be identified by manual inspection. Second, recent mainstream techniques the YOLOv4 neural network to the graphics card GPU core operator to speed up the recognition of defect images is being applied to the non-destructive inspection process of aircraft maintenance on A, C and D-Level, fully validating the deep learning model's powerful defect detection target capability. The attention-based YOLOv4 algorithm is improved by applying a one-stage attention mechanism to the YOLOv4, thereby improving the accuracy of the innovation model. Finally, thesis improved YOLOv4 based on an attention mechanism is proposed for object detection NDT via the deep learning method to effectively improve and shorten the inspection anomaly detection method for automatic detection sensor systems.

In the present, the growth of digitization and worldwide communications make OCR systems of exotic languages a very important task. In this paper, we attempt to develop an OCR system for one of these exotic languages with a unique script, Amharic. Motivated by the recent success of the Attention mechanism in Neural Machine Translation (NMT), we extend the attention mechanism for Amharic text-image recognition. The proposed model consists of CNNs and attention embedded recurrent encoder-decoder networks that are integrated following the configuration of the seq2seq framework. The attention network parameters are trained in an end-to-end fashion and the context vector is injected, with the previously predicted output, at each time steps of decoding. Unlike the existing OCR model that minimizes the CTC objective function, the new model minimizes the categorical cross-entropy loss. The performance of the proposed attention-based model is evaluated against the test dataset from the ADOCR database which consists of both printed and synthetically generated Amharic text-line images and achieved promising results with a CER of 1.54% and 1.17% respectively.

Targets detection in synthetic aperture radar (SAR) remote sensing images, which is a fundamental but challenging problem in the field of satellite image analysis, plays an important role for a wide range of applications and is receiving significant attention in recent years. Besides, the ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of SAR image scene still remains a challenge. This paper analyzes the defects and shortcomings of traditional visual models applied to SAR images. Then a visual attention model designed for SAR images is proposed. The model draws the basic framework of classical ITTI model; selects and extracts the texture features and other features that can describe the SAR image better. We proposes a new algorithm for computing the local texture saliency of the input image, then the model constructs the corresponding saliency maps of features; Next, a new mechanism of feature fusion is adopted to replace the linear additive mechanism of classical models to obtain the overall saliency map; Finally, the gray-scale characteristics of focus of attention (FOA) in saliency map of all features are taken into account, our model choose the best saliency representation, Through the multi-scale competition strategy, the filter and threshold segmentation of the saliency maps can be used to select the salient regions accurately, thereby completing this operation for the visual saliency detection in SAR images. In the paper, several types of satellite image data, such as TerraSAR-X (TS-X), Radarsat-2, are used to evaluate the performance of visual models. The results show that our model provides superior performance compared with classical visual models. By further contrasting with the classical visual models, Our model reduce the false alarm caused by speckle noise, and its detection speed is greatly improved, and it is increased by 25% to 45%.

Using traditional methods based on detection rules written by human security experts, there is a significant challenge in accurately detecting many network threats that are increasingly becoming sophisticated. In order to deal with the limitation of the traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads containing binary data as well as text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets, such as IP addresses and ports. Given the combination of these features, we ensemble a text 1D-CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique with the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC) currently operating in South Korea. The proposed model showed remarkable progress compared to previous studies, demonstrating a highly accurate classification performance with an F1-Score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute to help security agents in the field divert their time to analyzing more complex attack patterns.

Research shows that stress, a common problem in dense cities, can be relieved in the natural environment. As great significance has been attached to the urban environment and public health in the society, this paper aims to study the relation and interaction between the perceived sensory dimension of urban park green space, attention restoration and state empathy. Therefore, we conducted an on-site questionnaire survey in four typical parks in Chengdu in terms of age, sex, daily stress, frequency of access in parks and other basic information of the respondents. The main part consists of perceived dimension, state empathy and attention restoration. The software SPSS24.0 is applied to the test of the validity and reliability of the PSD Scale, and then the important correlation between the perceived sensory dimensions in the parks and visitors' attention restoration is analyzed through multiple linear regression. Finally, the moderation effect of state empathy is tested by PROCESS. The findings show that (1) only seven dimensions in the PSD Scale are effective; (2) Serene and Refuge in the perceived sensory dimensions have significant effect on the restorative components of attention. (3) Except the dimensions of Rich in Species and Refuge, empathy enhanced the moderation effect in the interaction between the other five dimensions the Perceived Restorative Scale(PRS), especially in the interaction between the dimension Social and PRS. However, this study needs to be further explored to provide scientific basis and design strategy guidance for the research on the restoration potential of urban park green space in high-density urban areas.

With the development of deep learning, several Graph Neural Networks (GNN)-based approaches have been utilized for text classification. However, GNNs encounter challenges in capturing contextual text information within a document sequence. To address this, a novel text classification model RB-GAT is proposed by combining RoBERTa-BiGRU embedding and a multi-head Graph ATtention Network (GAT). First, the pre-trained RoBERTa model is exploited to learn word and text embeddings in different contexts. Second, the Bidirectional Gated Recurrent Unit (BiGRU) is employed to capture long-term dependencies and bidirectional sentence information from the text context. Next, the multi-head graph attention network is applied to analyze this information, which serves as a node feature for the document. Finally, the classification results are generated through a Softmax layer. Experimental results on three benchmark datasets demonstrate that our method can achieve an accuracy of 71.48%, 98.45%, and 80.32% on Ohsumed, R8, and MR, which is superior to the existing nine text classification approaches.

The unstable international economic situation is reflected in the supply chain stress, lack or increased cost of some raw materials, fuel or semi-finished products is forcing organizations to perform new optimization initiatives in the utilization of their equipment and assets pointed to obtain the maximum value from them, while maintaining and even improving the quality of their products. The achievement of these objectives involves the reduction or minimization of equipment downtime to maintain the advantage over their competitors and ensure the organization's competitiveness. The intelligent maintenance system (IMS) provides adequate support for decision-making related to equipment maintenance, since poor maintenance results in unplanned stoppages, with the consequent additional cost and increased customer dissatisfaction, and an over-maintenance can result in an additional labor cost, time and the replacement of parts that are in good conditions. The utilization of new tools and technologies introduced by Industry 4.0 offers multiple opportunities for enhancement through communication and computerized data processing, aiming to improve the maintainability of a hydrogen compressor using neural networks based on attention mechanisms combined with linear regression.

(1) Background: There is robust evidence of an attention bias-anxiety relationship in children, but lack of appropriate methods has limited the number of studies with children younger than 8 years old. This study used eye-tracking as a measure of overt attention in young children. The aim of this study was to assess anxiety related attention bias in children aged 4 to 8 years. Age was considered as a moderator and the influence of effortful control was investigated. (2) Method: A community sample of 104 children were shown pairs of happy-neutral and angry-neutral faces. Growth curve analyses were used to examine patterns of gaze over time. (3) Results: Analyses revealed moderation by age and anxiety, with distinct patterns of anxiety-related biases seen in different age groups in the angry-neutral face trials. Effortful control did not account for age related effects. (4) Conclusions: Results support a moderation model of the development of anxiety in children.

Ensuring the accuracy of wind power prediction is paramount for the reliable and stable operation of power systems. This study introduces a novel approach aimed at enhancing the precision of wind power prediction through the development of a multiscale hybrid model. This model integrates advanced methodologies including Improved Intrinsic Mode Function with Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), Permutation Entropy(PE), Least Squares Support Vector Regression (LSSVR), Regularized Extreme Learning Machine(RELM), Multi-head Attention (MHA), and Bidirectional Gated Recurrent Unit (BiGRU). Firstly, the ICEEMDAN technique is employed to decompose the non-stationary raw wind power data into multiple relatively stable sub-modes, while concurrently utilizing PE to assess the complexity of each sub-mode. Secondly, the dataset is reconstituted into three distinct components: high-frequency, mid-frequency, and low-frequency, to alleviate data complexity. Following this, the LSSVR, RELM, and MHA-BiGRU models are individually applied to predict the high, mid,and low-frequency components, respectively. Thirdly, the parameters of the low-frequency prediction model are optimized utilizing the Dung Betele Optimizer(DBO) algorithm. Ultimately, the predicted results of each component are aggregated to derive the final prediction. Empirical findings illustrate the exceptional predictive performance of the multiscale hybrid model incorporating LSSVR, RELM,and MHA-BiGRU. In comparison to other benchmark models, the proposed model exhibits a reduction in Root Mean Square Error(RMSE) values of over 10%, conclusively affirming its superior predictive accuracy.

In the remote sensing domain, it is crucial to complete semantic segmentation on the raster images, e.g., river, building, forest, etc, on raster images. A deep convolutional encoder--decoder (DCED) network is the state-of-the-art semantic segmentation method for remotely sensed images. However, the accuracy is still limited, since the network is not designed for remotely sensed images and the training data in this domain is deficient. In this paper, we aim to propose a novel CNN for semantic segmentation particularly for remote sensing corpora with three main contributions. First, we propose applying a recent CNN called a global convolutional network (GCN), since it can capture different resolutions by extracting multi-scale features from different stages of the network. Additionally, we further enhance the network by improving its backbone using larger numbers of layers, which is suitable for medium resolution remotely sensed images. Second, "channel attention'' is presented in our network in order to select the most discriminative filters (features). Third, "domain-specific transfer learning'' is introduced to alleviate the scarcity issue by utilizing other remotely sensed corpora with different resolutions as pre-trained data. The experiment was then conducted on two given datasets: (i) medium resolution data collected from Landsat-8 satellite and (ii) very high resolution data called the ISPRS Vaihingen Challenge Dataset. The results show that our networks outperformed DCED in terms of $F1$ for 17.48% and 2.49% on medium and very high resolution corpora, respectively.

Talker variability has been reported to facilitate generalization and retention of speech learning, but is also shown to place demands on cognitive resources. Our recent study provided evidence that phonetically-irrelevant acoustic variability in single-talker (ST) speech is sufficient to induce equivalent amounts of learning to the use of multiple-talker (MT) training. This study is a follow-up contrasting MT versus ST training with varying degrees of temporal exaggeration to examine how cognitive measures of individual learners may influence the role of input variability in immediate learning and long-term retention. Native Chinese-speaking adults were trained on the English /i/-/ɪ/ contrast. We assessed the trainees’ working memory and selective attention before training. Trained participants showed retention of more native-like cue weighting in both perception and production regardless of talker variability condition. The ST training group showed long-term benefit in word identification, whereas the MT training group did not retain the improvement. The results demonstrate the role of phonetically-irrelevant variability in robust speech learning and modulatory functions of nonlinguistic working memory and selective attention, highlighting the necessity to consider the interaction between input characteristics, task difficulty, and individual differences in cognitive abilities in assessing learning outcomes.