{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:02:18Z","timestamp":1770739338507,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icmew63481.2024.10645440","type":"proceedings-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T13:43:36Z","timestamp":1724939016000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["SFMVIT: Slowfast Meet VIT in Chaotic World"],"prefix":"10.1109","author":[{"given":"Jiaying","family":"Lin","sequence":"first","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Wen","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L.","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baiqiao","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00953"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref8","article-title":"The kinetics human action video dataset","author":"Kay","year":"(2017)","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.34133\/cbsystems.0002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01849"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"ref13","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","volume-title":"International Conference on Machine Learning. PMLR.","author":"Ryali"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"ref17","article-title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","author":"Wang","year":"(2024)","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01398"},{"key":"ref19","article-title":"InternVide02: Scaling Video Foundation Models for Multimodal Video Understanding","author":"Wang","year":"(2024)","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01414"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2019.2929005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01323"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10645349\/10645352\/10645440.pdf?arnumber=10645440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:00:49Z","timestamp":1770670849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icmew63481.2024.10645440","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}