{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T14:41:39Z","timestamp":1778510499578,"version":"3.51.4"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00467","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4808-4817","source":"Crossref","is-referenced-by-count":1,"title":["Structured Context Learning for Generic Event Boundary Detection"],"prefix":"10.1109","author":[{"given":"Xin","family":"Gu","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Congcong","family":"Li","sequence":"additional","affiliation":[{"name":"Sichuan Changhong Electric Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyao","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dexiang","family":"Hong","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiejian","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longyin","family":"Wen","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Fan","sequence":"additional","affiliation":[{"name":"University of North Texas,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_16"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23192-1_67"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806316"},{"key":"ref4","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.338"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref7","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","article-title":"Generic event boundary detection challenge at CVPR 2021 technical report: Cascaded temporal attention network (CASTANET)","author":"Hong","year":"2021","journal-title":"CoRR"},{"key":"ref15","first-page":"495","article-title":"3d convolutional neural networks for human action recognition","volume-title":"ICML","author":"Ji","year":"2010"},{"key":"ref16","article-title":"Winning the cvpr\u20192021 kinetics-gebd challenge: Contrastive learning approach","author":"Kang","year":"2021","journal-title":"CoRR"},{"key":"ref17","article-title":"Uboco : Unsupervised boundary contrastive learning for generic event boundary detection","author":"Kang","year":"2021","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01944"},{"key":"ref19","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"CoRR"},{"key":"ref20","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01358"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","article-title":"Video swin transformer","author":"Liu","year":"2021","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref29","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"Luo","year":"2016","journal-title":"NIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref34","article-title":"Discerning generic event boundaries in long-form wild videos","author":"Rai","year":"2021","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00275"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref39","article-title":"Transnet V2: an effective deep network architecture for fast shot transition detection","author":"Soucek","year":"2020","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3283067"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00335"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_36"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780195376746.013.0006"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2986861"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.342"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681513"},{"key":"ref54","article-title":"Face transformer for recognition","author":"Zhong","year":"2021","journal-title":"CoRR"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492676.pdf?arnumber=11492676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:59:28Z","timestamp":1778047168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00467","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}