{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-large-scale-study-on-unsupervised","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","arxiv_id":"2104.14558","date":"2021-04-29","proceeding":"CVPR 2021 1","authors":["Christoph Feichtenhofer","Haoqi Fan","Bo Xiong","Ross Girshick","Kaiming He"],"abstract":"We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to space-time. Our objective encourages temporally-persistent features in the same video, and in spite of its simplicity, it works surprisingly well across: (i) different unsupervised frameworks, (ii) pre-training datasets, (iii) downstream datasets, and (iv) backbone architectures. We draw a series of intriguing observations from this study, e.g., we discover that encouraging long-spanned persistency can be effective even if the timespan is 60 seconds. In addition to state-of-the-art results in multiple benchmarks, we report a few promising cases in which unsupervised pre-training can outperform its supervised counterpart. Code is made available at https://github.com/facebookresearch/SlowFast","url_abs":"https://arxiv.org/abs/2104.14558v1","url_pdf":"https://arxiv.org/pdf/2104.14558v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-large-scale-study-on-unsupervised","repo_url":"https://github.com/facebookresearch/SlowFast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-large-scale-study-on-unsupervised","repo_url":"https://github.com/seleucia/goca","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-action-recognition","task_name":"Self-Supervised Action Recognition"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"pBYOL","rank_in_archive_order":3,"of":48,"metrics":{"Frozen":"false","Pre-Training Dataset":"Kinetics400","Top-1 Accuracy":"75.0"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101","task":"Self-Supervised Action Recognition","dataset":"UCF101","model":"pBYOL","rank_in_archive_order":5,"of":53,"metrics":{"3-fold Accuracy":"96.3","Frozen":"false","Pre-Training Dataset":"Kinetics400"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.14558","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}