{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:25:20Z","timestamp":1755926720922,"version":"3.37.3"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100015803","name":"Tencent Data Platform","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3227425","type":"journal-article","created":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T20:40:45Z","timestamp":1670445645000},"page":"128959-128969","source":"Crossref","is-referenced-by-count":2,"title":["Tencent AVS: A Holistic Ads Video Dataset for Multi-Modal Scene Segmentation"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9658-5127","authenticated-orcid":false,"given":"Jie","family":"Jiang","sequence":"first","affiliation":[{"name":"Tencent Data Platform, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9635-5671","authenticated-orcid":false,"given":"Zhimin","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6840-8262","authenticated-orcid":false,"given":"Jiangfeng","family":"Xiong","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1221-4140","authenticated-orcid":false,"given":"Rongwei","family":"Quan","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4584-0826","authenticated-orcid":false,"given":"Qinglin","family":"Lu","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3865-8145","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461404"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.01.001"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641075"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref36","first-page":"206","article-title":"NeXtVLAD: An efficient neural network to aggregate frame-level features for large-scale video classification","volume":"11132","author":"lin","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021756"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00705"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2017.8227441"},{"key":"ref62","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2823900"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"ref65","article-title":"Truly multi-modal YouTube-8M video classification with video, audio, and text","author":"wang","year":"2017","journal-title":"arXiv 1706 05461"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref67","article-title":"Audiovisual SlowFast networks for video recognition","author":"xiao","year":"2020","journal-title":"arXiv 2001 08740"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref1","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016","journal-title":"arXiv 1609 08675"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0548-3"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref54","article-title":"TransNet V2: An effective deep network architecture for fast shot transition detection","author":"soucek","year":"2020","journal-title":"arXiv 2008 04838"},{"key":"ref53","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":"ref52","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc NIPS"},{"journal-title":"Pyscenedetect Intelligent scene cut detection and video splitting tool","year":"2018","author":"castellano","key":"ref10"},{"key":"ref11","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","author":"damen","year":"2018","journal-title":"arXiv 1804 02748"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_35"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref3","first-page":"1","article-title":"Self-supervised multimodal versatile networks","author":"alayrac","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref6","article-title":"Asymmetric loss for multi-label classification","author":"baruch","year":"2020","journal-title":"arXiv 2009 14119"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806316"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.28"},{"key":"ref7","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","volume":"139","author":"bertasius","year":"2021","journal-title":"Proc ICML"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1142\/S1793351X17400086"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref41","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"1967","journal-title":"Proc 5th Berkeley Symp Math Statist Probab"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126682"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09973306.pdf?arnumber=9973306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T21:25:18Z","timestamp":1673299518000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9973306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3227425","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}