{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T17:15:27Z","timestamp":1782062127857,"version":"3.54.5"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,3,1]],"date-time":"2018-03-01T00:00:00Z","timestamp":1519862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["ZYGX2014J063"],"award-info":[{"award-number":["ZYGX2014J063"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["ZYGX2014Z007"],"award-info":[{"award-number":["ZYGX2014Z007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61502080"],"award-info":[{"award-number":["61502080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61632007"],"award-info":[{"award-number":["61632007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1109\/tmm.2017.2749159","type":"journal-article","created":{"date-parts":[[2017,9,4]],"date-time":"2017-09-04T18:07:45Z","timestamp":1504548465000},"page":"634-644","source":"Crossref","is-referenced-by-count":224,"title":["Two-Stream 3-D convNet Fusion for Action Recognition in Videos With Arbitrary Size and Length"],"prefix":"10.1109","volume":"20","author":[{"given":"Xuanhan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref33","first-page":"204","article-title":"Beyond Gaussian pyramid: Multi-skip feature stacking for action recognition","author":"lan","year":"0","journal-title":"Proc Conf Comput Vis and Pattern Recog"},{"key":"ref32","first-page":"3337","author":"liu","year":"2011","journal-title":"Recognizing Human Actions by Attributes"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1109\/TBC.2015.2419824","article-title":"Efficient motion and disparity estimation optimization for low complexity multiview video coding","volume":"61","author":"pan","year":"2015","journal-title":"IEEE Trans Broadcast"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2016.07.018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2233723"},{"key":"ref40","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref13","first-page":"3487","article-title":"Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition","author":"gan","year":"0","journal-title":"Proc Amer Assoc Artif Intell"},{"key":"ref14","first-page":"3530","article-title":"Labeling the features not the samples: Efficient video classification with minimal supervision","author":"leordeanu","year":"0","journal-title":"Proc Amer Assoc Artif Intell"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref18","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":"ref19","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"0","journal-title":"Proc Amer Assoc Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2699863"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2505180"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.021"},{"key":"ref29","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2729896"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964308"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2271746"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601260"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964295"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref22","article-title":"Towards good practices for very deep two-stream convnets","author":"wang","year":"2015","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref24","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 Recogn"},{"key":"ref41","first-page":"214","article-title":"A duality based approach for realtime TV-L1 optical flow","author":"zach","year":"0","journal-title":"Proc Symp German Assoc Pattern Recognition"},{"key":"ref23","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8291714\/08025706.pdf?arnumber=8025706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:25:31Z","timestamp":1642004731000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8025706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3]]},"references-count":41,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2749159","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3]]}}}