{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:40Z","timestamp":1777657480339,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tnnls.2023.3263387","type":"journal-article","created":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T17:29:25Z","timestamp":1683221365000},"page":"12507-12517","source":"Crossref","is-referenced-by-count":13,"title":["CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4435-7098","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3133-3644","authenticated-orcid":false,"given":"Jingen","family":"Liu","sequence":"additional","affiliation":[{"name":"JD AI Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"JD AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.127.1.3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00681"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477701"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.140"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/200"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01234"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00873"},{"key":"ref14","article-title":"Joint visual-temporal embedding for unsupervised learning of actions in untrimmed sequences","author":"VidalMata","year":"2020","journal-title":"arXiv:2001.11122"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.11.004"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8721.2007.00480.x"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1037\/0882-7974.21.3.466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"ref20","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.004"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00771"},{"key":"ref26","article-title":"Unsupervised learning by predicting noise","author":"Bojanowski","year":"2017","journal-title":"arXiv:1704.05310"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00129"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref29","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv:2002.05709"},{"key":"ref30","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020","journal-title":"arXiv:2006.09882"},{"key":"ref31","article-title":"EnAET: A self-trained framework for semi-supervised and supervised learning with ensemble transformations","author":"Wang","year":"2019","journal-title":"arXiv:1911.09265"},{"key":"ref32","article-title":"Adversarial feature learning","author":"Donahue","year":"2016","journal-title":"arXiv:1605.09782"},{"key":"ref33","first-page":"10542","article-title":"Large scale adversarial representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Donahue"},{"key":"ref34","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"Asano","year":"2019","journal-title":"arXiv:1911.05371"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref38","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"arXiv:2006.07733"},{"key":"ref39","article-title":"AdCo: Adversarial contrast for efficient learning of unsupervised representations from self-trained negative adversaries","author":"Hu","year":"2020","journal-title":"arXiv:2011.08435"},{"key":"ref40","article-title":"Self-supervised co-training for video representation learning","author":"Han","year":"2020","journal-title":"arXiv:2010.09709"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00058"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref45","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref46","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref47","article-title":"BERT has a mouth, and it must speak: BERT as a Markov random field language model","author":"Wang","year":"2019","journal-title":"arXiv:1902.04094"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.216"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref52","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref53","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10663876\/10115309.pdf?arnumber=10115309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:14:54Z","timestamp":1725473694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10115309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":53,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3263387","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}