{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:06Z","timestamp":1740132846902,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61370129","61375062","61632004"],"award-info":[{"award-number":["61370129","61375062","61632004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"PCSIRT","award":["IRT201206"],"award-info":[{"award-number":["IRT201206"]}]},{"DOI":"10.13039\/100007000","name":"Laboratory Directed Research & Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007000","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006227","name":"Lawrence Livermore National Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006227","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Dept. of Energy","award":["DE-AC52-07NA27344"],"award-info":[{"award-number":["DE-AC52-07NA27344"]}]},{"name":"Science and Technology Bureau of Baoding City","award":["16ZG026"],"award-info":[{"award-number":["16ZG026"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/tmm.2017.2703939","type":"journal-article","created":{"date-parts":[[2017,5,12]],"date-time":"2017-05-12T17:47:11Z","timestamp":1494611231000},"page":"2637-2650","source":"Crossref","is-referenced-by-count":10,"title":["DCAR: A Discriminative and Compact Audio Representation for Audio Processing"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2160-1721","authenticated-orcid":false,"given":"Liping","family":"Jing","sequence":"first","affiliation":[]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jaeyoung","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Adam","family":"Janin","sequence":"additional","affiliation":[]},{"given":"Julia","family":"Bernd","sequence":"additional","affiliation":[]},{"given":"Michael W.","family":"Mahoney","sequence":"additional","affiliation":[]},{"given":"Gerald","family":"Friedland","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"1973","author":"brent","journal-title":"Algorithms for Minimization Without Derivatives","key":"ref38"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1002\/0470013192.bsa501"},{"key":"ref32","first-page":"1601","article-title":"Self-tuning spectral clustering","author":"zelnik-manor","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1145\/2812802"},{"year":"2012","author":"over","article-title":"TRECVID 2011—An overview of the goals,\n tasks, data, evaluation mechanisms, and metrics","key":"ref30"},{"key":"ref37","first-page":"547","article-title":"Multivariate\n autoregressive mixture models for music auto-tagging","author":"coviello","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/TASL.2010.2090148"},{"key":"ref35","article-title":"CP-JKU submissions for DCASE-2016: A\n hybrid approach using binaural i-vectors and deep convolutional neural networks","author":"eghbal-zadeh","year":"0","journal-title":"Detection and Classification of Acoustic Scenes and Events"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1145\/2814815.2814816"},{"key":"ref11","first-page":"2085","article-title":"Event-based video retrieval using audio","author":"jin","year":"0","journal-title":"Proc INTERSPEECH"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/2072508.2072513"},{"key":"ref13","first-page":"2282","article-title":"A blind segmentation approach to acoustic event detection asked on i-vector","author":"huang","year":"0","journal-title":"Proc INTERSPEECH"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ISM.2013.27"},{"key":"ref15","article-title":"Recurrence\n quantification analysis features for auditory scene classification","author":"roma","year":"2013","journal-title":"IEEE AASP Challenge Detection and Classification of Acoustic Scenes and Events"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/TASL.2007.913750"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/TASL.2010.2064307"},{"year":"2002","author":"scholkopf","journal-title":"Learning with kernels","key":"ref18"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TIP.2012.2206040"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1515\/9781400830244"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TMM.2012.2199972"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1137\/050637996"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TMM.2010.2050650"},{"key":"ref6","first-page":"801","article-title":"Ambient sound provides supervision for visual learning","author":"owens","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"year":"2015","author":"bernd","article-title":"The YLI-MED corpus: Characteristics,\n procedures, and plans (TR-15-001)","key":"ref29"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TMM.2015.2428998"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/MSP.2014.2326181"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TMM.2013.2267205"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TMM.2008.921739"},{"key":"ref9","first-page":"529","article-title":"Audio-based context\n awareness—Acoustic modeling and perceptual evaluation","author":"eronen","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1145\/2964284.2970377"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/TPAMI.2008.110"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/TIP.2017.2746993"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSP.2017.7952132"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/TNN.2005.860852"},{"year":"2004","author":"mclachlan","journal-title":"Discriminant Analysis and Statistical Pattern Recognition","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICCV.2011.6126523"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1007\/s11263-005-3222-z"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8110760\/07927482.pdf?arnumber=7927482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:39:42Z","timestamp":1641987582000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7927482\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":38,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2703939","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}