Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- short-paperOctober 2016
Ad Recommendation for Sponsored Search Engine via Composite Long-Short Term Memory
MM '16: Proceedings of the 24th ACM international conference on MultimediaOctober 2016, Pages 416–420https://doi.org/10.1145/2964284.2967254Search engine logs contain a large amount of users' click-through data that can be leveraged as implicit indicators of relevance. In this paper we address ad recommendation problem that finding and ranking the most relevant ads with respect to users' ...
- research-articleAugust 2015
Semi-supervised Hashing with Semantic Confidence for Large Scale Visual Search
SIGIR '15: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information RetrievalAugust 2015, Pages 53–62https://doi.org/10.1145/2766462.2767725Similarity search is one of the fundamental problems for large scale multimedia applications. Hashing techniques, as one popular strategy, have been intensively investigated owing to the speed and memory efficiency. Recent research has shown that ...
- short-paperNovember 2014
Click-through-based Subspace Learning for Image Search
MM '14: Proceedings of the 22nd ACM international conference on MultimediaNovember 2014, Pages 233–236https://doi.org/10.1145/2647868.2656404One of the fundamental problems in image search is to rank image documents according to a given textual query. We address two limitations of the existing image search engines in this paper. First, there is no straightforward way of comparing textual ...
- research-articleNovember 2014
Rescue Tail Queries: Learning to Image Search Re-rank via Click-wise Multimodal Fusion
MM '14: Proceedings of the 22nd ACM international conference on MultimediaNovember 2014, Pages 537–546https://doi.org/10.1145/2647868.2654900Image search engines have achieved good performance for head (popular) queries by leveraging text information and user click data. However, there still remain a large number of tail (rare) queries with relatively unsatisfying search results, which are ...
- research-articleJuly 2014
Click-through-based cross-view learning for image search
SIGIR '14: Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrievalJuly 2014, Pages 717–726https://doi.org/10.1145/2600428.2609568One of the fundamental problems in image search is to rank image documents according to a given textual query. Existing search engines highly depend on surrounding texts for ranking images, or leverage the query-image pairs annotated by human labelers ...
-
- research-articleOctober 2013
Image search by graph-based label propagation with image representation from DNN
MM '13: Proceedings of the 21st ACM international conference on MultimediaOctober 2013, Pages 397–400https://doi.org/10.1145/2502081.2508128Our objective is to estimate the relevance of an image to a query for image search purposes. We address two limitations of the existing image search engines in this paper. First, there is no straightforward way of bridging the gap between semantic ...
- research-articleOctober 2013
Annotation for free: video tagging by mining user search behavior
MM '13: Proceedings of the 21st ACM international conference on MultimediaOctober 2013, Pages 977–986https://doi.org/10.1145/2502081.2502085The problem of tagging is mostly considered from the perspectives of machine learning and data-driven philosophy. A fundamental issue that underlies the success of these approaches is the visual similarity, ranging from the nearest neighbor search to ...
- ArticleJune 2013
Modeling semantic and behavioral relations for query suggestion
WAIM'13: Proceedings of the 14th international conference on Web-Age Information ManagementJune 2013, Pages 666–678https://doi.org/10.1007/978-3-642-38562-9_68Query suggestion helps users to precisely express their search intents. The state-of-the-art approaches make great progress on high-frequency queries via click graphs. However, due to query ambiguity and click-through data sparseness, these approaches ...
- ArticleDecember 2012
An Improved Method for Combination Feature Selection in Web Click-Through Data Mining
ISISE '12: Proceedings of the 2012 Fourth International Symposium on Information Science and EngineeringDecember 2012, Pages 381–385https://doi.org/10.1109/ISISE.2012.92An important way to analyze the web click-through data is to build up a 2-class linear classifier, and select a key subset from user's features which mainly decided the hit result. But in many circumstances, the fitting accuracy is not good as the model ...
- research-articleOctober 2011
Mining Concept Sequences from Large-Scale Search Logs for Context-Aware Query Suggestion
ACM Transactions on Intelligent Systems and Technology (TIST), Volume 3, Issue 1Article No.: 17, Pages 1–40https://doi.org/10.1145/2036264.2036281Query suggestion plays an important role in improving usability of search engines. Although some recently proposed methods provide query suggestions by mining query patterns from search logs, none of them models the immediately preceding queries as ...
- posterMarch 2011
A kernel approach to addressing term mismatch
WWW '11: Proceedings of the 20th international conference companion on World wide webMarch 2011, Pages 153–154https://doi.org/10.1145/1963192.1963270This paper addresses the problem of dealing with term mismatch in web search using 'blending'. In blending, the input query as well as queries similar to it are used to retrieve documents, the ranking results of documents with respect to the queries are ...
- ArticleDecember 2010
Learning Document Labels from Enriched Click Graphs
ICDMW '10: Proceedings of the 2010 IEEE International Conference on Data Mining WorkshopsDecember 2010, Pages 57–64https://doi.org/10.1109/ICDMW.2010.190Document classification plays an increasingly important role in extracting and organizing the knowledge, however, the Web document classification task was hindered by the huge number of Web documents while limited resource of human judgment on the ...
- posterOctober 2010
Expected browsing utility for web search evaluation
CIKM '10: Proceedings of the 19th ACM international conference on Information and knowledge managementOctober 2010, Pages 1561–1564https://doi.org/10.1145/1871437.1871672Most information retrieval evaluation metrics are designed to measure the satisfaction of the user given the results returned by a search engine. In order to evaluate user satisfaction, most of these metrics have underlying user models, which aim at ...
- posterOctober 2010
User behavior driven ranking without editorial judgments
CIKM '10: Proceedings of the 19th ACM international conference on Information and knowledge managementOctober 2010, Pages 1473–1476https://doi.org/10.1145/1871437.1871650We explore the potential of using users click-through logs where no editorial judgment is available to improve the ranking function of a vertical search engine. We base our analysis on the Cumulate Relevance Model, a user behavior model recently ...
- research-articleJuly 2010
Learning more powerful test statistics for click-based retrieval evaluation
SIGIR '10: Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrievalJuly 2010, Pages 507–514https://doi.org/10.1145/1835449.1835534Interleaving experiments are an attractive methodology for evaluating retrieval functions through implicit feedback. Designed as a blind and unbiased test for eliciting a preference between two retrieval functions, an interleaved ranking of the results ...
- ArticleJuly 2010
Detecting hot events from web search logs
WAIM'10: Proceedings of the 11th international conference on Web-age information managementJuly 2010, Pages 417–428Detecting events from web resources is a challenging task, attracting many attentions in recent years. Web search log is an important data source for event detection because the information it contains reflects users' activities and interestingness to ...
- posterNovember 2009
Exploring relevance for clicks
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementNovember 2009, Pages 1847–1850https://doi.org/10.1145/1645953.1646246Mining feedback information from user click-through data is an important issue for modern Web retrieval systems in terms of architecture analysis, performance evaluation and algorithm optimization. For commercial search engines, user click-through data ...
- research-articleNovember 2009
Improving web page classification by label-propagation over click graphs
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementNovember 2009, Pages 1077–1086https://doi.org/10.1145/1645953.1646090In this paper, we present a semi-supervised learning method for web page classification, leveraging click logs to augment training data by propagating class labels to unlabeled similar documents. Current state-of-the-art classifiers are supervised and ...
- posterJuly 2009
Enhancing topical ranking with preferences from click-through data
SIGIR '09: Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrievalJuly 2009, Pages 666–667https://doi.org/10.1145/1571941.1572068To overcome the training data insufficiency problem for dedicated model in topical ranking, this paper proposes to utilize click-through data to improve learning. The efficacy of click-through data is explored under the framework of preference learning. ...
- research-articleJune 2009
A Markov chain model for integrating behavioral targeting into contextual advertising
ADKDD '09: Proceedings of the Third International Workshop on Data Mining and Audience Intelligence for AdvertisingJune 2009, Pages 1–9https://doi.org/10.1145/1592748.1592750Both Contextual Advertising (CA) and Behavioral Targeting (BT) are playing important roles in online advertising market. Recently, the problem of how to integrate BT strategies into CA has attracted much attention from both industry and academia. ...