Browse wiki

Jump to: navigation, search
Comprehensive query-dependent fusion using regression-on-folksonomies: A case study of multimodal music search
Abstract The combination of heterogeneous knowledgeThe combination of heterogeneous knowledge sources has been widely regarded as an effective approach to boost retrieval accuracy in many information retrieval domains. While various technologies have been recently developed for information retrieval, multimodal music search has not kept pace with the enormous growth of data on the Internet. In this paper, we study the problem of integrating multiple online information sources to conduct effective query dependent fusion (QDF) of multiple search experts for music retrieval. We have developed a novel framework to construct a knowledge space of users' information need from online folksonomy data. With this innovation, a large number of comprehensive queries can be automatically constructed to train a better generalized QDF system against unseen user queries. In addition, our framework models QDF problem by regression of the optimal combination strategy on a query. Distinguished from the previous approaches, the regression model of QDF (RQDF) offers superior modeling capability with less constraints and more efficient computation. To validate our approach, a large scale test collection has been collected from different online sources, such as Last.fm, Wikipedia, and YouTube. All test data will be released to the public for better research synergy in multimodal music search. Our performance study indicates that the accuracy, efficiency, and robustness of the multimodal music search can be improved significantly by the proposed folksonomy-RQDF approach. In addition, since no human involvement is required to collect training examples, our approach offers great feasibility and practicality in system development. Copyright 2009 ACM.in system development. Copyright 2009 ACM.
Abstractsub The combination of heterogeneous knowledgeThe combination of heterogeneous knowledge sources has been widely regarded as an effective approach to boost retrieval accuracy in many information retrieval domains. While various technologies have been recently developed for information retrieval, multimodal music search has not kept pace with the enormous growth of data on the Internet. In this paper, we study the problem of integrating multiple online information sources to conduct effective query dependent fusion (QDF) of multiple search experts for music retrieval. We have developed a novel framework to construct a knowledge space of users' information need from online folksonomy data. With this innovation, a large number of comprehensive queries can be automatically constructed to train a better generalized QDF system against unseen user queries. In addition, our framework models QDF problem by regression of the optimal combination strategy on a query. Distinguished from the previous approaches, the regression model of QDF (RQDF) offers superior modeling capability with less constraints and more efficient computation. To validate our approach, a large scale test collection has been collected from different online sources, such as Last.fm, Wikipedia, and YouTube. All test data will be released to the public for better research synergy in multimodal music search. Our performance study indicates that the accuracy, efficiency, and robustness of the multimodal music search can be improved significantly by the proposed folksonomy-RQDF approach. In addition, since no human involvement is required to collect training examples, our approach offers great feasibility and practicality in system development. Copyright 2009 ACM.in system development. Copyright 2009 ACM.
Bibtextype inproceedings  +
Doi 10.1145/1631272.1631303  +
Has author Bin Zhang + , Xiang Q. + , Lu H. + , Shen J. + , Yafang Wang +
Has extra keyword Efficient computation + , Folksonomies + , Framework models + , Heterogeneous Knowledge + , Information need + , Information retrieval domain + , Knowledge spaces + , Large scale tests + , Last.fm + , Modeling capabilities + , Multi-modal + , Multimodal search + , Multiple search + , Music retrieval + , On-line information + , Online sources + , Optimal combination + , Performance study + , Regression model + , Retrieval accuracy + , System development + , Test data + , Training example + , User query + , Wikipedia + , YouTube + , Information retrieval + , Information services + , Internet + , Method of moments + , Multimedia systems + , Technical presentations + , Regression analysis +
Has keyword Folksonomy + , Multimodal search + , Music + , Query-dependent fusion +
Isbn 9781605586083  +
Language English +
Number of citations by publication 0  +
Number of references by publication 0  +
Pages 213–222  +
Published in MM'09 - Proceedings of the 2009 ACM Multimedia Conference, with Co-located Workshops and Symposiums +
Title Comprehensive query-dependent fusion using regression-on-folksonomies: A case study of multimodal music search +
Type conference paper  +
Year 2009 +
Creation dateThis property is a special property in this wiki. 7 November 2014 07:22:31  +
Categories Publications without license parameter  + , Publications without remote mirror parameter  + , Publications without archive mirror parameter  + , Publications without paywall mirror parameter  + , Conference papers  + , Publications without references parameter  + , Publications  +
Modification dateThis property is a special property in this wiki. 7 November 2014 07:22:31  +
DateThis property is a special property in this wiki. 2009  +
hide properties that link here 
Comprehensive query-dependent fusion using regression-on-folksonomies: A case study of multimodal music search + Title
 

 

Enter the name of the page to start browsing from.