{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:05:41Z","timestamp":1770149141126,"version":"3.49.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2013,12,1]],"date-time":"2013-12-01T00:00:00Z","timestamp":1385856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/tmm.2013.2280437","type":"journal-article","created":{"date-parts":[[2013,11,13]],"date-time":"2013-11-13T19:01:46Z","timestamp":1384369306000},"page":"1830-1842","source":"Crossref","is-referenced-by-count":7,"title":["Query-Document-Dependent Fusion: A Case Study of Multimodal Music Retrieval"],"prefix":"10.1109","volume":"15","author":[{"given":"Zhonghua","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialie","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4175.001.0001","author":"scholkopf","year":"2001","journal-title":"Learning With Kernels-Support Vector Machines Regularization Optimization and Beyond"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916345"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148228"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/215206.215357"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101339"},{"key":"ref37","article-title":"Meta-search and federation using query difficulty prediction","author":"yom-tov","year":"2005","journal-title":"Proc ACM SIGIR Query Prediction Workshop"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076121"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284946"},{"key":"ref34","first-page":"451","article-title":"TRECVID: Benchmarking the effectiveness of information retrieval tasks on digital video","author":"smeaton","year":"2003","journal-title":"Proc CIVR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631303"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/584792.584908"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2071949"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71496-5_78"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459382"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2008.96"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1816123.1816146"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2012913"},{"key":"ref28","first-page":"345","article-title":"Learning to retrieve information","author":"bartell","year":"1995","journal-title":"Proc Swedish Conf Connectionism"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291465"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_18"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459386"},{"key":"ref6","first-page":"603","article-title":"Musiclef: A benchmark activity in multimodal music information retrieval","author":"orio","year":"2011","journal-title":"Proc ISMIR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/4236.707692"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.884618"},{"key":"ref8","article-title":"Experimenting vireo-374: Bags-of-visual-words and visualbased ontology for semantic video indexing and search","author":"ngo","year":"2007","journal-title":"Proc NIST TRECVID Workshop"},{"key":"ref7","first-page":"243","article-title":"Combination of multiple searches","author":"shaw","year":"1994","journal-title":"Proc TREC-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027661"},{"key":"ref9","article-title":"Trecvid 2004 search and feature extraction task by nus pris","author":"chua","year":"2004","journal-title":"Proc NIST TRECVID Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860449"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572011"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390273"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/34.667881"},{"key":"ref21","first-page":"675","article-title":"Music genre classification by ensembles of audio and lyrics features","author":"mayer","year":"2011","journal-title":"Proc ISMIR"},{"key":"ref42","first-page":"73","article-title":"Okapi at TREC-4","author":"rrobertson","year":"1995","journal-title":"NIST Special Publication 500-236 TREC-4"},{"key":"ref24","first-page":"2391","article-title":"Multimodal information fusion for video concept detection","author":"wu","year":"2004","journal-title":"Proc IEEE ICIP"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1108\/eb046814"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MUE.2007.96"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273598"},{"key":"ref26","first-page":"513","article-title":"Heterogeneous embedding for subjective artist similarity","author":"mcfee","year":"2009","journal-title":"Proc ISMIR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/S1355771800003071"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027665"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/6663669\/06588600.pdf?arnumber=6588600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T20:28:22Z","timestamp":1746044902000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6588600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":45,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2013.2280437","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,12]]}}}