{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:36:12Z","timestamp":1778891772541,"version":"3.51.4"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,5,1]],"date-time":"2017-05-01T00:00:00Z","timestamp":1493596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"National Nature Science Foundation","award":["61171118"],"award-info":[{"award-number":["61171118"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/lsp.2017.2689921","type":"journal-article","created":{"date-parts":[[2017,3,30]],"date-time":"2017-03-30T22:29:12Z","timestamp":1490912952000},"page":"712-716","source":"Crossref","is-referenced-by-count":19,"title":["Sequential Segment Networks for Action Recognition"],"prefix":"10.1109","volume":"24","author":[{"given":"Quan-Qi","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Jin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref30","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0859-0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2283846"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2598878"},{"key":"ref12","first-page":"392","article-title":"Modeling\n temporal structure of decomposable motion segments for activity classification","author":"niebles","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.65"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2295753"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref28","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref3","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc 27th Int Conf Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref29","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015"},{"key":"ref5","first-page":"20","article-title":"Temporal segment networks: Towards good\n practices for deep action recognition","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2293060"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2404779"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref22","article-title":"Long-term\n temporal convolutions for action recognition","author":"varol","year":"2016"},{"key":"ref21","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2529686"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref26","article-title":"Ucf101: A\n dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.219"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/7885156\/07890436.pdf?arnumber=7890436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:27:49Z","timestamp":1642004869000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7890436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":34,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lsp.2017.2689921","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5]]}}}