Svoboda | Graniru | BBC Russia | Golosameriki | Facebook
Skip to main content
  • Finland
Research Interests:
This paper presents a task-based user evaluation of two content-based image database browsing systems. The performance of the two systems is compared to that of a commercial image database management program, which does not employ... more
This paper presents a task-based user evaluation of two content-based image database browsing systems. The performance of the two systems is compared to that of a commercial image database management program, which does not employ content-based information. Experimental results show that content-based cues improve the efficiency of the browsing considerably. Guidelines for system design are derived from the user feedback.
... follows. Chapter 2 describes the methodology, defining the three color features used in this study and the (dis)similarity measures. Chapter 3 presents the experiments, image data and retrieval results for the three methods. ...
University of Oulu's MediaTeam research group participated to the manual and interactive search tasks with our video retrieval system, which is constructed out of three... more
University of Oulu's MediaTeam research group participated to the manual and interactive search tasks with our video retrieval system, which is constructed out of three sub-applications: Content-based Query Tool, Cluster-Temporal Browser and Result Container with relevance feedback mechanism. The search engine in the heart of our search system creates result sets using three distinct search sub-engines that take care of
Research Interests:
Abstract This paper studies the performance sensitivity of the variations in different factors on SNoW and SVM based face detection techniques. These factors include combinations of training set, pixel transitions in sliding window,... more
Abstract This paper studies the performance sensitivity of the variations in different factors on SNoW and SVM based face detection techniques. These factors include combinations of training set, pixel transitions in sliding window, pre-processing methods (rotation, scaling, ...
Research Interests:
In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames.... more
In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames. Power-related physical features are extracted from short audio samples in video shots. Video shots containing people, cityscape, landscape, speech or instrumental sound are detected with trained self-organized maps and kNN classification results of audio samples. Test runs and evaluations in TREC 2002 Video Track show consistent performance for Temporal Gradient Correlogram and state-of-the-art precision in audio-based instrumental sound detection.
Peer-to-peer service-oriented community coordinated multimedia (SCCM) is envisioned as a novel paradigm in which the user consumes multiple media through requesting multimedia-intensive Web services via diversity display devices,... more
Peer-to-peer service-oriented community coordinated multimedia (SCCM) is envisioned as a novel paradigm in which the user consumes multiple media through requesting multimedia-intensive Web services via diversity display devices, converged networks, and heterogeneous platforms within a virtual, open and collaborative community. In this paper, a generic P2P SCCM scenario is created and examined first. A SCCM model is designed with the adoption of the service orientation approach and principles. A tunneled hierarchical P2P model is designed and its performance is analyzed for improving service lookup and session setup. A preliminary SCCM prototype is developed with the design of content annotation service.
While the mobile television market is still young, mobile TV represents an emerging hotbed for multimedia applications because it brings traditional TV services and on-demand audiovisual content to mobile devices. According to the latest... more
While the mobile television market is still young, mobile TV represents an emerging hotbed for multimedia applications because it brings traditional TV services and on-demand audiovisual content to mobile devices. According to the latest European Union report on mobile TV, the technology is receiving a strong worldwide interest. South Korea, for example, is at the forefront of mobile TV development. And in Japan, there are more than seven million mobile TV users. Moreover, in the US, mobile phone users have been ...
Abstract Pervasive Service Composition (PSC) incorporates service composition and pervasive computing into managing user's everyday activities. A generic Reference... more
Abstract Pervasive Service Composition (PSC) incorporates service composition and pervasive computing into managing user's everyday activities. A generic Reference Model of Pervasive Service Composition (PSC-RM) is needed for guiding PSC architecture design and implementation. To design PSC-RM, we first investigate and present a user's generic activity model. Then we analyze characteristics of PSC and envision PSC applications. Based on these applications we present requirements and initial design of PSC-RM.
This paper describes distributed web service architecture to allow web level scalability for multimedia content analysis. We introduce service component architecture that allows for orchestration and composition of services as content... more
This paper describes distributed web service architecture to allow web level scalability for multimedia content analysis. We introduce service component architecture that allows for orchestration and composition of services as content analysis units to enrich multimedia metadata using common data model built upon MPEG-7 content description standard. We report experiments with automatic load balancing and introduce an end user application that facilitates annotation of people in images and video.
Abstract Peer-to-peer service-oriented community coordinated multimedia (SCCM) is envisioned as a novel paradigm in which the user consumes multiple media through requesting multimedia-intensive Web services via diversity display devices,... more
Abstract Peer-to-peer service-oriented community coordinated multimedia (SCCM) is envisioned as a novel paradigm in which the user consumes multiple media through requesting multimedia-intensive Web services via diversity display devices, converged networks, and heterogeneous platforms within a virtual, open and collaborative community in context of a novel concept of multimedia applications as Web services. A generic P2P SCCM scenario is created and examined first. The SCCM model is designed with respect ...
Community Coordinated Multimedia (CCM) empowers users' experiences through providing services of multimedia aggregation, delivery, sharing, and viewing within a community via the Internet. This paper approaches the CCM paradigm a step by... more
Community Coordinated Multimedia (CCM) empowers users' experiences through providing services of multimedia aggregation, delivery, sharing, and viewing within a community via the Internet. This paper approaches the CCM paradigm a step by designing and developing Digital Movie Guide (DMG) service for enhancing user's viewing experience. The DMG service prototype is implemented and demonstrated.