{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:24:48Z","timestamp":1760955888565,"version":"3.37.3"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1109\/tmm.2018.2871418","type":"journal-article","created":{"date-parts":[[2018,9,20]],"date-time":"2018-09-20T21:55:37Z","timestamp":1537480537000},"page":"887-901","source":"Crossref","is-referenced-by-count":10,"title":["Weakly-Supervised Visual Instrument-Playing Action Detection in Videos"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1299-6688","authenticated-orcid":false,"given":"Jen-Yu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8960-9995","authenticated-orcid":false,"given":"Shyh-Kang","family":"Jeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","first-page":"1","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref33","article-title":"Look, listen and learn","author":"arandjelovi?","year":"2017","journal-title":"arXiv 1705 08168"},{"key":"ref32","article-title":"CortexNet: A generic network family for robust visual temporal representations","author":"canziani","year":"2017","journal-title":"arXiv 1706 02735"},{"key":"ref31","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CVPR.2016.309"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1145\/2964284.2964292"},{"key":"ref36","first-page":"44","article-title":"Learning to pinpoint singing voice from weakly labeled examples","author":"schl\u00fcter","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1145\/2964284.2964310"},{"key":"ref34","article-title":"See, hear, and read: Deep aligned representations","author":"aytar","year":"2017","journal-title":"arXiv 1706 00932"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/CVPR.2014.15"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1007\/978-3-642-33863-2_20"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/CVPR.2012.6248065"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TMM.2017.2666540"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TMM.2015.2404779"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/3078971.3079002"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/TMM.2016.2581582"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/s11263-015-0816-y"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/5.726791"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2015.7298668"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1007\/BF00994018"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1145\/3065386"},{"key":"ref50","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/ICCV.2015.169"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TMM.2015.2496372"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/TMM.2014.2307552"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/CVPR.2015.7298965"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/TMM.2013.2265531"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TSA.2005.860351"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TMM.2010.2098858"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP.2014.6854599"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/TASLP.2016.2632307"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/TMM.2017.2674603"},{"key":"ref18","first-page":"30","article-title":"Left and right-hand guitar playing techniques detection","author":"reboursi\u00e8re","year":"0","journal-title":"Proc Int Conf New Interfaces for Musical Expression"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1145\/2926719"},{"key":"ref4","first-page":"1","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/978-3-319-10602-1_41"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TMM.2015.2436813"},{"key":"ref5","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","volume":"7 12","author":"ng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/978-3-319-46493-0_9"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2016.213"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1109\/CVPR.2016.119"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP.2017.7952688"},{"key":"ref46","first-page":"387","article-title":"Evaluation of algorithms using games: the case of music tagging","author":"law","year":"0","journal-title":"Proc 10th Int Soc Music Inf Retrieval Conf"},{"key":"ref45","first-page":"155","article-title":"Medleydb: A multitrack dataset for annotation-intensive MIR research","author":"bittner","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref48","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1007\/978-3-319-16814-2_16"},{"year":"2017","author":"mcfee","article-title":"librosa 0.5.0","key":"ref42"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/3-540-45103-X_50","article-title":"Two-frame motion estimation based on polynomial expansion","author":"farneb\u00e4ck","year":"2003","journal-title":"Image Analysis"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref43","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016","journal-title":"arXiv 1609 08675"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8672836\/08468056.pdf?arnumber=8468056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:50:18Z","timestamp":1657745418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8468056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":51,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2871418","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2019,4]]}}}