{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T18:46:14Z","timestamp":1791485174398,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475272","type":"proceedings-article","created":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T23:03:42Z","timestamp":1672959822000},"page":"917-925","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":107,"title":["Token Shift Transformer for Video Classification"],"prefix":"10.1145","author":[{"given":"Hao","family":"Zhang","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020"},{"key":"e_1_3_2_2_2_1","volume-title":"Language Models are Few-Shot Learners. (2020). arxiv","author":"Brown Tom B.","year":"2005"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00741"},{"key":"e_1_3_2_2_7_1","unstructured":"Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tamas Sarlos Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser etal 2020. Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020).  Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tamas Sarlos Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser et al. 2020. Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020)."},{"key":"e_1_3_2_2_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018"},{"key":"e_1_3_2_2_9_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly etal 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).  Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_30"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_2_13_1","volume-title":"large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677","author":"Goyal Priya","year":"2017"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416276"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413595"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_17_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev Nikita","year":"2020"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 619--635","author":"Li Yin"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01233"},{"key":"e_1_3_2_2_23_1","volume-title":"Two-stream convolutional networks for action recognition in videos. arXiv preprint arXiv:1406.2199","author":"Simonyan Karen","year":"2014"},{"key":"e_1_3_2_2_24_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"e_1_3_2_2_26_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413764"},{"key":"e_1_3_2_2_28_1","volume-title":"2020 a. Training data-efficient image transformers & distillation through attention. arXiv preprint arXiv:2012.12877","author":"Touvron Hugo","year":"2020"},{"key":"e_1_3_2_2_29_1","volume-title":"2020 b. Training data-efficient image transformers & distillation through attention. arXiv preprint arXiv:2012.12877","author":"Touvron Hugo","year":"2020"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_31_1","volume-title":"Attention is all you need. arXiv preprint arXiv:1706.03762","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_3_2_2_32_1","volume-title":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection. arXiv preprint arXiv:2104.09770","author":"Wang Junke","year":"2021"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"e_1_3_2_2_35_1","volume-title":"2020 b. End-to-End Video Instance Segmentation with Transformers. arXiv preprint arXiv:2011.14503","author":"Wang Yuqing","year":"2020"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6918"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00951"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413916"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12528-011-9042-y"},{"key":"e_1_3_2_2_41_1","volume-title":"Shiftaddnet: A hardware-inspired deep network. arXiv preprint arXiv:2010.12785","author":"You Haoran","year":"2020"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.3169\/mta.4.218"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2884478"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01445"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413809"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475272","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:17Z","timestamp":1750193297000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475272"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":45,"alternative-id":["10.1145\/3474085.3475272","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475272","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}