{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:06:59Z","timestamp":1766732819174,"version":"3.37.3"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan","award":["2016YFB1001004"],"award-info":[{"award-number":["2016YFB1001004"]}]},{"name":"Guangdong Science and Technology Project","award":["2017B010123003"],"award-info":[{"award-number":["2017B010123003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772161"],"award-info":[{"award-number":["61772161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/tmm.2019.2907453","type":"journal-article","created":{"date-parts":[[2019,3,25]],"date-time":"2019-03-25T18:20:12Z","timestamp":1553538012000},"page":"2518-2530","source":"Crossref","is-referenced-by-count":18,"title":["Exploiting Mid-Level Semantics for Large-Scale Complex Video Classification"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9544-9801","authenticated-orcid":false,"given":"Ji","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8119-3726","authenticated-orcid":false,"given":"Kuizhi","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4923-0910","authenticated-orcid":false,"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref37","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/182.358466"},{"article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"soomro","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2823900"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964328"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.178"},{"article-title":"UC merced submission to the ActivityNet challenge 2016","year":"2017","author":"zhu","key":"ref63"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"article-title":"Untrimmed video classification for activity detection: Submission to ActivityNet challenge","year":"2016","author":"singh","key":"ref64"},{"key":"ref27","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2844101"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2855081"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref25","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.107"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50077-5_3"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.288"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749406"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref56","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/212"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-017-9538-x"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2518700"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"3463","DOI":"10.1109\/TNNLS.2017.2728139","article-title":"Multiview privileged support vector machines","volume":"29","author":"tang","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"article-title":"CUHK & ETHZ & SIAT submission to ActivityNet challenge 2016","year":"2016","author":"xiong","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545513"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911832"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2510329"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2004912"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2009703"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2559947"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2763322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0024-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.06.042"},{"key":"ref9","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":"ref46","first-page":"3464","article-title":"Dynamic concept composition for zero-example event detection","author":"chang","year":"0","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806221"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.339"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref41","first-page":"1378","article-title":"Object bank: A high-level image representation for scene classification & semantic feature sparsification","author":"li","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.329"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6475038"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8846791\/08673926.pdf?arnumber=8673926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:47:06Z","timestamp":1657745226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8673926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":64,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2907453","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2019,10]]}}}