{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T13:54:24Z","timestamp":1789998864169,"version":"4.0.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"PKU-NTU Joint Research Institute"},{"name":"Ng Teng Fong Charitable Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1109\/tmm.2018.2862341","type":"journal-article","created":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T18:34:58Z","timestamp":1533148498000},"page":"416-428","source":"Crossref","is-referenced-by-count":118,"title":["Unified Spatio-Temporal Attention Networks for Action Recognition in Videos"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9936-1126","authenticated-orcid":false,"given":"Dong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7587-101X","authenticated-orcid":false,"given":"Ting","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4491-2023","authenticated-orcid":false,"given":"Ling-Yu","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Rui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806226"},{"key":"ref70","article-title":"The LEAR submission at THUMOS 2014","author":"oneata","year":"0","journal-title":"Proc THUMOS Challenge Workshop Eur Conf Comput Vis"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref33","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"mansimov","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref31","article-title":"Recurrent tubelet proposal and recognition networks for action detection","author":"li","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref30","article-title":"MSR ASIA MSM at ActivityNet Challenge 2017","author":"yao","year":"0","journal-title":"Proc ActivityNet Challenge Workshop Conf Comput Vision Pattern Recognit"},{"key":"ref37","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2017.11.005"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.333"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-016-0117-4"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0723-7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref63","first-page":"178-1","article-title":"Event fisher vectors: Robust encoding visual diversity of visual streams","author":"nagel","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref64","first-page":"3832","article-title":"Learning deep intrinsic video representation by exploring temporal coherence and graph structure","author":"pan","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref65","first-page":"435","article-title":"Evaluating two-stream CNN for video classification","author":"ye","year":"0","journal-title":"Proc ACM Int Conf Multimedia Retrieval"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.517"},{"key":"ref29","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref69","article-title":"Action recognition and detection by combining motion and appearance features","author":"wang","year":"0","journal-title":"Proc THUMOS Challenge Workshop Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"ref22","article-title":"University of Amsterdam at THUMOS Challenge 2014","author":"jain","year":"0","journal-title":"Proc THUMOS Challenge Workshop Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.345"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref23","article-title":"MSR ASIA MSM at THUMOS Challenge 2015","author":"qiu","year":"0","journal-title":"Proc THUMOS Challenge Workshop Conf Comput Vis Pattern Recognit"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.435"},{"key":"ref50","article-title":"THUMOS Challenge: Action recognition with a large number of classes","author":"jiang","year":"0","journal-title":"THUMOS Challenge Workshop Eur Conf Comput Vis"},{"key":"ref51","first-page":"142","article-title":"Exploiting objects with LSTMs for video categorization","author":"sun","year":"0","journal-title":"Proc ACM Multimedia"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref55","first-page":"60-1","article-title":"Exploiting image-trained CNN architectures for unconstrained video classification","author":"zha","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912001"},{"key":"ref11","article-title":"Action recognition using visual attention","author":"sharma","year":"0","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref40","article-title":"Hierarchical attention network for action recognition in videos","author":"wang","year":"2016","journal-title":"arXiv 1607 06416"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref14","first-page":"650","article-title":"An efficient dense and scale-invariant spatio-temporal interest point detector","author":"willems","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2404779"},{"key":"ref19","first-page":"143","article-title":"Improving the fisher kernel for large-scale image classification","author":"perronnin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477242"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2674622"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2436813"},{"key":"ref8","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref45","first-page":"1245","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref48","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref47","first-page":"214","article-title":"A duality based approach for realtime TV-l1 optical flow","author":"zach","year":"0","journal-title":"Proc DAGM-Symp Pattern Recognition"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8625851\/08424031.pdf?arnumber=8424031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:58:21Z","timestamp":1657745901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8424031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":72,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2862341","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2]]}}}