{"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/contextualized-spatio-temporal-contrastive","title":"Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision","arxiv_id":"2112.05181","date":"2021-12-09","proceeding":"CVPR 2022 1","authors":["Liangzhe Yuan","Rui Qian","Yin Cui","Boqing Gong","Florian Schroff","Ming-Hsuan Yang","Hartwig Adam","Ting Liu"],"abstract":"Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for learning spatio-temporally fine-grained features in videos, where scenes and instances evolve through space and time. In this paper, we present Contextualized Spatio-Temporal Contrastive Learning (ConST-CL) to effectively learn spatio-temporally fine-grained video representations via self-supervision. We first design a region-based pretext task which requires the model to transform in-stance representations from one view to another, guided by context features. Further, we introduce a simple network design that successfully reconciles the simultaneous learning process of both holistic and local representations. We evaluate our learned representations on a variety of downstream tasks and show that ConST-CL achieves competitive results on 6 datasets, including Kinetics, UCF, HMDB, AVA-Kinetics, AVA and OTB.","url_abs":"https://arxiv.org/abs/2112.05181v2","url_pdf":"https://arxiv.org/pdf/2112.05181v2.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":"contextualized-spatio-temporal-contrastive","repo_url":"https://github.com/tensorflow/models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"contextualized-spatio-temporal-contrastive","repo_url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/temporal-normalizing-flows","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"spatio-temporal-action-localization","task_name":"Spatio-Temporal Action Localization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.05181","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}