{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:33:56Z","timestamp":1780104836941,"version":"3.54.0"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccvw69036.2025.00094","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"863-873","source":"Crossref","is-referenced-by-count":2,"title":["Simplifying Traffic Anomaly Detection with Video Foundation Models"],"prefix":"10.1109","author":[{"given":"Svetlana","family":"Orlova","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tommie","family":"Kerssies","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno B.","family":"Englert","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gijs","family":"Dubbelman","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref2","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on ma-chine learning","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-023-00322-4"},{"key":"ref6","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen"},{"key":"ref7","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00651"},{"key":"ref9","article-title":"An image is worth 16x16 words: Trans-formers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3044678"},{"key":"ref11","article-title":"Cognitive accident prediction in driving scenes: A multimodality benchmark","author":"Fang","year":"2022","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01241"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICICNIS64247.2024.10823129"},{"key":"ref17","article-title":"The kinetics hu-man action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"First Place Solution to the ECCV 2024 BRAVO Challenge: Eval-uating Robustness of Vision Foundation Models for Seman-tic Segmentation","author":"Kerssies","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02356"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301978"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3390173"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3553830"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00684"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019325"},{"key":"ref31","article-title":"Moeslund. Foundation models for video understanding: A survey","author":"Madan","year":"2024","journal-title":"Authorea Preprints"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00272"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref34","article-title":"Trecvit: A re-current video transformer","author":"Patraucean","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3572428"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervi-sion","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447554"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_17"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827228"},{"key":"ref40","article-title":"U cf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2022.09.012"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00790"},{"key":"ref44","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00675"},{"key":"ref46","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91585-7_18"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00732"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451070"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3150763"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00271"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3147826"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11374628.pdf?arnumber=11374628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:32:39Z","timestamp":1771918359000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11374628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00094","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}