{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T19:18:32Z","timestamp":1773947912680,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2017,9,1]],"date-time":"2017-09-01T00:00:00Z","timestamp":1504224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Prime Minister's Office, Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IRC@SG Funding Initiative"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/tmm.2017.2722687","type":"journal-article","created":{"date-parts":[[2017,7,11]],"date-time":"2017-07-11T19:36:55Z","timestamp":1499801815000},"page":"2080-2092","source":"Crossref","is-referenced-by-count":25,"title":["VideoWhisper: Toward Discriminative Unsupervised Video Feature Learning With Attention-Based Recurrent Neural Networks"],"prefix":"10.1109","volume":"19","author":[{"given":"Na","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1007\/978-3-642-35289-8_30","article-title":"Learning feature representations with K-means","author":"coates","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref31","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref37","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref36","article-title":"The new data and new challenges in multimedia research","author":"thomee","year":"2015","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref10","first-page":"5532","article-title":"Visual translation embedding network for visual relation detection","author":"zhang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref12","article-title":"MOSIFT: Recognizing human actions in surveillance videos","author":"chen","year":"2009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref15","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref18","article-title":"Video (language) modeling: A baseline for generative models of natural videos","author":"ranzato","year":"2014","journal-title":"CoRR"},{"key":"ref19","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMS","author":"srivastava","year":"2015","journal-title":"Proc ICML"},{"key":"ref28","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806338"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2436813"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2456412"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2315780"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2610324"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2271746"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019344"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8010475\/07974787.pdf?arnumber=7974787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:03:48Z","timestamp":1642003428000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7974787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":37,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2722687","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9]]}}}