{"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/end-to-end-semi-supervised-learning-for-video","title":"End-to-End Semi-Supervised Learning for Video Action Detection","arxiv_id":"2203.04251","date":"2022-03-08","proceeding":"CVPR 2022 1","authors":["Akash Kumar","Yogesh Singh Rawat"],"abstract":"In this work, we focus on semi-supervised learning for video action detection which utilizes both labeled as well as unlabeled data. We propose a simple end-to-end consistency based approach which effectively utilizes the unlabeled data. Video action detection requires both, action class prediction as well as a spatio-temporal localization of actions. Therefore, we investigate two types of constraints, classification consistency, and spatio-temporal consistency. The presence of predominant background and static regions in a video makes it challenging to utilize spatio-temporal consistency for action detection. To address this, we propose two novel regularization constraints for spatio-temporal consistency; 1) temporal coherency, and 2) gradient smoothness. Both these aspects exploit the temporal continuity of action in videos and are found to be effective for utilizing unlabeled videos for action detection. We demonstrate the effectiveness of the proposed approach on two different action detection benchmark datasets, UCF101-24 and JHMDB-21. In addition, we also show the effectiveness of the proposed approach for video object segmentation on the Youtube-VOS which demonstrates its generalization capability The proposed approach achieves competitive performance by using merely 20% of annotations on UCF101-24 when compared with recent fully supervised methods. On UCF101-24, it improves the score by +8.9% and +11% at 0.5 f-mAP and v-mAP respectively, compared to supervised approach.","url_abs":"https://arxiv.org/abs/2203.04251v3","url_pdf":"https://arxiv.org/pdf/2203.04251v3.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":"end-to-end-semi-supervised-learning-for-video","repo_url":"https://github.com/AKASH2907/End-to-End-Semi-Supervised-Learning-for-Video-Action-Detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"classification-consistency","task_name":"Classification Consistency"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-action-detection","task_name":"Semi-Supervised Video Action Detection"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"},{"task_slug":"video-action-detection","task_name":"Video Action Detection"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-detection-on-ucf101-24","task":"Action Detection","dataset":"UCF101-24","model":"E2E-SSL (I3D)","rank_in_archive_order":12,"of":19,"metrics":{"Frame-mAP 0.5":"69.9","Video-mAP 0.5":"72.1"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.04251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04251"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AKASH2907/End-to-End-Semi-Supervised-Learning-for-Video-Action-Detection","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"10b51853924fe349","entry":"CapsuleLoss","repo":"AKASH2907/End-to-End-Semi-Supervised-Learning-for-Video-Action-Detection","repo_kind":"official","path":"utils/losses.py","file_url":"https://github.com/AKASH2907/End-to-End-Semi-Supervised-Learning-for-Video-Action-Detection/blob/HEAD/utils/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10b51853924fe349"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}