{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T12:22:44Z","timestamp":1777897364035,"version":"3.51.4"},"reference-count":45,"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\/icmew63481.2024.10645423","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":4,"title":["A Survey on Backbones for Deep Video Action Recognition"],"prefix":"10.1109","author":[{"given":"Zixuan","family":"Tang","sequence":"first","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University,Shenzhen,China,518107"}]},{"given":"Youjun","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University,Shenzhen,China,518107"}]},{"given":"Yuhang","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University,Shenzhen,China,518107"}]},{"given":"Mengyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen Graduate School,National Key Laboratory of General Artificial Intelligence,Shenzhen,China,518055"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/encyclopedia2010031"},{"key":"ref2","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"issue":"3","key":"ref10","article-title":"Is space-time attention all you need for video under-standing","volume":"2","author":"Bertasius","year":"2021","journal-title":"pp. 4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"ref18","first-page":"7024","article-title":"Potion: Pose motion repre-sentation for action recognition","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recog-nition","author":"Choutas","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trit.2016.03.001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.129"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.590"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref28","author":"Sharir","year":"2021","journal-title":"An image is worth 16x16 words, what is a video worth?"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume":"34","author":"Patrick","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Space-time mixing attention for video transformer","volume":"34","author":"Bulat","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00333"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01398"},{"key":"ref34","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","year":"2023"},{"key":"ref35","article-title":"Uniformer: Uni-fied transformer for efficient spatial-temporal representation learning","volume-title":"International Conference on Learning Representations, 2022","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.161"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"ref41","author":"Wang","journal-title":"Internvideo: General video foundation models via generative and discriminative learning"},{"key":"ref42","author":"Yao","journal-title":"Side4video: Spatial-temporal side network for memory-efficient image-to-video transfer learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref44","author":"Kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.622"}],"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\/10645423.pdf?arnumber=10645423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:48:42Z","timestamp":1760032122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icmew63481.2024.10645423","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}