{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:28:57Z","timestamp":1782862137310,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":26,"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\/3474085.3478329","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T20:00:05Z","timestamp":1634587205000},"page":"3783-3786","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":45,"title":["PyTorchVideo"],"prefix":"10.1145","author":[{"given":"Haoqi","family":"Fan","sequence":"first","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tullie","family":"Murrell","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Wang","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kalyan Vasudev","family":"Alwala","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanghao","family":"Li","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilei","family":"Li","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Xiong","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikhila","family":"Ravi","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haichuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jitendra","family":"Malik","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross","family":"Girshick","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matt","family":"Feiszli","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Adcock","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wan-Yen","family":"Lo","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Feichtenhofer","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In ICML.  Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In ICML."},{"key":"e_1_3_2_1_2_1","unstructured":"Cisco. 2020. Annual Internet Report (2018--2023) White Paper.  Cisco. 2020. Annual Internet Report (2018--2023) White Paper."},{"key":"e_1_3_2_1_3_1","unstructured":"MMAction2 Contributors. 2020. OpenMMLab's Next Generation Video Under- standing Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmaction2.  MMAction2 Contributors. 2020. OpenMMLab's Next Generation Video Under- standing Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmaction2."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"e_1_3_2_1_5_1","volume-title":"Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray.","author":"Damen Dima","year":"2018","unstructured":"Dima Damen , Hazel Doughty , Giovanni Maria Farinella , Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray. 2018 . Scaling Egocentric Vision: The EPIC- KITCHENS Dataset. In ECCV. Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray. 2018. Scaling Egocentric Vision: The EPIC- KITCHENS Dataset. In ECCV."},{"key":"e_1_3_2_1_6_1","unstructured":"Haoqi Fan Yanghao Li Bo Xiong Wan-Yen Lo and Christoph Feichtenhofer. 2020. PySlowFast. https:\/\/github.com\/facebookresearch\/slowfast.  Haoqi Fan Yanghao Li Bo Xiong Wan-Yen Lo and Christoph Feichtenhofer. 2020. PySlowFast. https:\/\/github.com\/facebookresearch\/slowfast."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Haoqi Fan Bo Xiong Karttikeya Mangalam Yanghao Li Zhicheng Yan Jitendra Malik and Christoph Feichtenhofer. 2021. Multiscale Vision Transformers.  Haoqi Fan Bo Xiong Karttikeya Mangalam Yanghao Li Zhicheng Yan Jitendra Malik and Christoph Feichtenhofer. 2021. Multiscale Vision Transformers.","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer. 2020. X3D: Expanding architectures for efficient video recognition. In CVPR.  Christoph Feichtenhofer. 2020. X3D: Expanding architectures for efficient video recognition. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer Haoqi Fan Jitendra Malik and Kaiming He. 2019. Slow- Fast networks for video recognition. In ICCV.  Christoph Feichtenhofer Haoqi Fan Jitendra Malik and Kaiming He. 2019. Slow- Fast networks for video recognition. In ICCV.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer Haoqi Fan Bo Xiong Ross Girshick and Kaiming He. 2021. A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning. In CVPR.  Christoph Feichtenhofer Haoqi Fan Bo Xiong Ross Girshick and Kaiming He. 2021. A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"e_1_3_2_1_11_1","volume-title":"Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, et al.","author":"Goyal Raghav","year":"2017","unstructured":"Raghav Goyal , Samira Ebrahimi Kahou , Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, et al. 2017 . The \"Something Something\" Video Database for Learning and Evaluating Visual Common Sense.. In ICCV. Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, et al. 2017. The \"Something Something\" Video Database for Learning and Evaluating Visual Common Sense.. In ICCV."},{"key":"e_1_3_2_1_12_1","volume-title":"Zhao- han Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R\u00e9mi Munos, and Michal Valko.","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill , Florian Strub , Florent Altch\u00e9 , Corentin Tallec , Pierre H. Richemond , Elena Buchatskaya , Carl Doersch , Bernardo Avila Pires , Zhao- han Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R\u00e9mi Munos, and Michal Valko. 2020 . Bootstrap your own latent: A new approach to self-supervised Learning. In NIPS. Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhao- han Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R\u00e9mi Munos, and Michal Valko. 2020. Bootstrap your own latent: A new approach to self-supervised Learning. In NIPS."},{"key":"e_1_3_2_1_13_1","volume-title":"Cordelia Schmid, and Jitendra Malik.","author":"Gu Chunhui","year":"2018","unstructured":"Chunhui Gu , Chen Sun , David A. Ross , Carl Vondrick , Caroline Pantofaru , Yeqing Li , Sudheendra Vijayanarasimhan , George Toderici , Susanna Ricco , Rahul Suk- thankar , Cordelia Schmid, and Jitendra Malik. 2018 . AVA : A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions. In CVPR. Chunhui Gu, Chen Sun, David A. Ross, Carl Vondrick, Caroline Pantofaru, Yeqing Li, Sudheendra Vijayanarasimhan, George Toderici, Susanna Ricco, Rahul Suk- thankar, Cordelia Schmid, and Jitendra Malik. 2018. AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions. In CVPR."},{"key":"e_1_3_2_1_14_1","unstructured":"Jian Guo He He Tong He Leonard Lausen Mu Li Haibin Lin Xingjian Shi Chenguang Wang Junyuan Xie Sheng Zha Aston Zhang Hang Zhang Zhi Zhang Zhongyue Zhang Shuai Zheng and Yi Zhu. 2020. GluonCV and Glu- onNLP: Deep Learning in Computer Vision and Natural Language Processing. In Journal of Machine Learning Research.  Jian Guo He He Tong He Leonard Lausen Mu Li Haibin Lin Xingjian Shi Chenguang Wang Junyuan Xie Sheng Zha Aston Zhang Hang Zhang Zhi Zhang Zhongyue Zhang Shuai Zheng and Yi Zhu. 2020. GluonCV and Glu- onNLP: Deep Learning in Computer Vision and Natural Language Processing. In Journal of Machine Learning Research."},{"key":"e_1_3_2_1_15_1","unstructured":"Kaiming He Haoqi Fan Yuxin Wu Saining Xie and Ross Girshick. 2021. Momentum Contrast for Unsupervised Visual Representation Learning. In CVPR.  Kaiming He Haoqi Fan Yuxin Wu Saining Xie and Ross Girshick. 2021. Momentum Contrast for Unsupervised Visual Representation Learning. In CVPR."},{"key":"e_1_3_2_1_16_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR."},{"key":"e_1_3_2_1_17_1","volume-title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty. ICLR","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks , Norman Mu , Ekin D. Cubuk , Barret Zoph , Justin Gilmer , and Balaji Lakshminarayanan . 2020. AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty. ICLR ( 2020 ). Dan Hendrycks, Norman Mu, Ekin D. Cubuk, Barret Zoph, Justin Gilmer, and Balaji Lakshminarayanan. 2020. AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty. ICLR (2020)."},{"key":"e_1_3_2_1_18_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev etal 2017. The kinetics human action video dataset. arXiv.  Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Gunnar A Sigurdsson G\u00fcl Varol Xiaolong Wang Ali Farhadi Ivan Laptev and Abhinav Gupta. 2016. Hollywood in homes: Crowdsourcing data collection for activity understanding. In ECCV.  Gunnar A Sigurdsson G\u00fcl Varol Xiaolong Wang Ali Farhadi Ivan Laptev and Abhinav Gupta. 2016. Hollywood in homes: Crowdsourcing data collection for activity understanding. In ECCV.","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_1_21_1","volume-title":"Nascimento","author":"Silva Michel","year":"2018","unstructured":"Michel Silva , Washington Ramos , Jo\u00e3o Ferreira , Felipe Chamone , Mario Campos , and Erickson R . Nascimento . 2018 . A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos. In CVPR. Michel Silva, Washington Ramos, Jo\u00e3o Ferreira, Felipe Chamone, Mario Campos, and Erickson R. Nascimento. 2018. A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos. In CVPR."},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. ICCV.","author":"Tran Du","year":"2019","unstructured":"Du Tran , Heng Wang , Lorenzo Torresani , and Matt Feiszli . 2019 . Video Classifi- cation with Channel-Separated Convolutional Networks . In Proc. ICCV. Du Tran, Heng Wang, Lorenzo Torresani, and Matt Feiszli. 2019. Video Classifi- cation with Channel-Separated Convolutional Networks. In Proc. ICCV."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Du Tran Heng Wang Lorenzo Torresani Jamie Ray Yann LeCun and Manohar Paluri. 2018. A closer look at spatiotemporal convolutions for action recognition. In CVPR.  Du Tran Heng Wang Lorenzo Torresani Jamie Ray Yann LeCun and Manohar Paluri. 2018. A closer look at spatiotemporal convolutions for action recognition. In CVPR.","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Xiaolong Wang Ross Girshick Abhinav Gupta and Kaiming He. 2018. Non-local Neural Networks. In CVPR.  Xiaolong Wang Ross Girshick Abhinav Gupta and Kaiming He. 2018. Non-local Neural Networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_26_1","volume-title":"Kristen Grauman, Jitendra Malik, and Christoph Fe- ichtenhofer.","author":"Xiao Fanyi","year":"2020","unstructured":"Fanyi Xiao , Yong Jae Lee , Kristen Grauman, Jitendra Malik, and Christoph Fe- ichtenhofer. 2020 . Audiovisual slowfast networks for video recognition. arXiv preprint arXiv:2001.08740 (2020). Fanyi Xiao, Yong Jae Lee, Kristen Grauman, Jitendra Malik, and Christoph Fe- ichtenhofer. 2020. Audiovisual slowfast networks for video recognition. arXiv preprint arXiv:2001.08740 (2020)."},{"key":"e_1_3_2_1_27_1","unstructured":"Dahua Lin Yue Zhao Yuanjun Xiong. 2019. MMAction. https:\/\/github.com\/ open-mmlab\/mmaction.  Dahua Lin Yue Zhao Yuanjun Xiong. 2019. MMAction. https:\/\/github.com\/ open-mmlab\/mmaction."}],"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\/3474085.3478329","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3478329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:26Z","timestamp":1750193306000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3478329"}},"subtitle":["A Deep Learning Library for Video Understanding"],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":26,"alternative-id":["10.1145\/3474085.3478329","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3478329","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"}}]}}