{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T08:05:13Z","timestamp":1776585913313,"version":"3.51.2"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2016,7,1]],"date-time":"2016-07-01T00:00:00Z","timestamp":1467331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"SenseTime Group Limited"},{"name":"General Research Fund"},{"name":"Research Grants Council of the Hong Kong SAR","award":["CUHK 416713"],"award-info":[{"award-number":["CUHK 416713"]}]},{"name":"Sino-Dutch Joint Scientific Thematic Research Program","award":["JSTP172644KYSB20150019"],"award-info":[{"award-number":["JSTP172644KYSB20150019"]}]},{"name":"Guangdong Innovative Research Program","award":["2015B010129013"],"award-info":[{"award-number":["2015B010129013"]}]},{"name":"Guangdong Innovative Research Program","award":["2014B050505017"],"award-info":[{"award-number":["2014B050505017"]}]},{"name":"Shenzhen Research Program","award":["KQCX2015033117354153"],"award-info":[{"award-number":["KQCX2015033117354153"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1109\/tmm.2016.2557722","type":"journal-article","created":{"date-parts":[[2016,4,21]],"date-time":"2016-04-21T18:15:14Z","timestamp":1461262514000},"page":"1305-1318","source":"Crossref","is-referenced-by-count":27,"title":["Bridging Music and Image via Cross-Modal Ranking Analysis"],"prefix":"10.1109","volume":"18","author":[{"given":"Xixuan","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaogang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoou","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"ref38","first-page":"2407","article-title":"Learning cross-modality similarity for multinomial data","author":"jia","year":"0","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2057231"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460114"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1509212.1509214"},{"key":"ref37","first-page":"918","article-title":"Maximum covariance unfolding: Manifold learning for bimodal data","author":"mahadevan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809682"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564482"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1321440.1321503"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206816"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2011.1"},{"key":"ref1","article-title":"Tunesensor: A semantic-driven music recommendation service for digital photo albums","author":"chao","year":"0","journal-title":"Proc Int Semantic Web Conf"},{"key":"ref20","first-page":"324","article-title":"Inferring efficient hierarchical taxonomies for MIR tasks: Application to musical instruments","author":"essid","year":"0","journal-title":"Proc 6th Int Conf Music Inf Retrieval"},{"key":"ref22","first-page":"433","article-title":"Learning visual attributes","author":"ferrari","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.913750"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543183"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459250"},{"key":"ref59","first-page":"888","article-title":"Normalized cuts and image segmentation","volume":"22","author":"shi","year":"2002","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref58","first-page":"207","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"weinberger","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref57","first-page":"1531","article-title":"Large scale multiple kernel learning","volume":"7","author":"sonnenburg","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref55","first-page":"451","article-title":"Metric learning by collapsing classes","author":"globerson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.3.792"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075150"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"ref10","first-page":"11","article-title":"Generalized non-metric multidimensional scaling","author":"agarwal","year":"0","journal-title":"Proc 11th Int Conf Artif Intell Statist"},{"key":"ref11","first-page":"491","article-title":"Learning multi-modal similarity","volume":"12","author":"mcfee","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070527"},{"key":"ref12","first-page":"41","article-title":"Learning a distance metric from relative comparisons","author":"schultz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745561"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291290"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911822"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref19","first-page":"151","article-title":"Features for audio and music classification","author":"mckinney","year":"0","journal-title":"Proc Int Symp Music Inf Retrieval"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396493"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396494"},{"key":"ref6","first-page":"133","article-title":"The mapping of thoughts, emotions, sensations, and images as responses to music","volume":"5","author":"osborne","year":"1981","journal-title":"J Mental Imagery"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X08005293"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2008.06.014"},{"key":"ref7","first-page":"105","article-title":"The facilitative effects of music on visual imagery: A multiple measures approach","volume":"7","author":"quittner","year":"1983","journal-title":"J Mental Imagery"},{"key":"ref49","first-page":"296","article-title":"Orientation histograms for hand gesture recognition","author":"freeman","year":"0","journal-title":"Proceedings International Workshop on Automatic Face- and Gesture-Recognition"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.7208\/chicago\/9780226521374.001.0001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995399"},{"key":"ref45","first-page":"661","article-title":"The earth movers distance, multi-dimensional scaling, and color-based image retrieval","author":"rubner","year":"0","journal-title":"Proc ARPA Image Understanding Workshop"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238354"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2036306"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2071944"},{"key":"ref44","article-title":"Mel frequency cepstral coefficients for music modeling","author":"logan","year":"0","journal-title":"Proc Int Symp Music Inf Retrieval"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1743384.1743400"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/7492217\/07457690.pdf?arnumber=7457690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:11:00Z","timestamp":1642003860000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7457690\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":59,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2016.2557722","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7]]}}}