{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:52:04Z","timestamp":1740178324943,"version":"3.37.3"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFC3302200"],"award-info":[{"award-number":["2022YFC3302200"]}]},{"name":"BUPT Innovation and Entrepreneurship Support Program","award":["2023-YC-A204","2024-YC-A137"],"award-info":[{"award-number":["2023-YC-A204","2024-YC-A137"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tetci.2024.3369866","type":"journal-article","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T18:18:24Z","timestamp":1710440304000},"page":"3001-3016","source":"Crossref","is-referenced-by-count":0,"title":["News-MESI: A Dataset for Multimodal News Excerpt Segmentation and Identification"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4616-2200","authenticated-orcid":false,"given":"Qing","family":"Song","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9249-3028","authenticated-orcid":false,"given":"Zilong","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7400-072X","authenticated-orcid":false,"given":"Wenhe","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8339-5081","authenticated-orcid":false,"given":"Wenyi","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7712-3322","authenticated-orcid":false,"given":"Mengjie","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2834-9461","authenticated-orcid":false,"given":"Chun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref2","article-title":"Uniformer: Unified transformer for efficient spatial-temporal representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00220"},{"key":"ref4","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_41"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00335"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01798"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00248"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01363"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_29"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126321"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00045"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_25"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2873722"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780195376746.013.0006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02039"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547839"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612371"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref28"},{"article-title":"A short note on the kinetics-700 human action dataset","year":"2019","author":"Carreira","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"article-title":"Bidirectional LSTM-CRF models for sequence tagging","year":"2015","author":"Huang","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"issue":"8","key":"ref34","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"article-title":"Youtube-8 m: A large-scale video classification benchmark","year":"2016","author":"Abu-El-Haija","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref37","first-page":"6360","article-title":"Surveillance face presentation attack detection challenge","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Escalera","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00910"},{"article-title":"THUMOS challenge: Action recognition with a large number of classes","year":"2015","author":"Gorban","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00705"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477701"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01103"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70711"},{"article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"Soomro","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3227425"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02039"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.778"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00272"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/6046.807953"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2823900"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.01.001"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0548-3"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.341"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2627563"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref75","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806316"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1142\/S1793351X17400086"},{"key":"ref82","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen","year":"2018"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_4"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73618-1_84"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10607834\/10464379.pdf?arnumber=10464379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T18:56:03Z","timestamp":1732647363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10464379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":88,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3369866","relation":{},"ISSN":["2471-285X"],"issn-type":[{"type":"electronic","value":"2471-285X"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}