{"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/video-cloze-procedure-for-self-supervised","title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","arxiv_id":"2001.00294","date":"2020-01-02","proceeding":null,"authors":["Dezhao Luo","Chang Liu","Yu Zhou","Dongbao Yang","Can Ma","Qixiang Ye","Weiping Wang"],"abstract":"We propose a novel self-supervised method, referred to as Video Cloze Procedure (VCP), to learn rich spatial-temporal representations. VCP first generates \"blanks\" by withholding video clips and then creates \"options\" by applying spatio-temporal operations on the withheld clips. Finally, it fills the blanks with \"options\" and learns representations by predicting the categories of operations applied on the clips. VCP can act as either a proxy task or a target task in self-supervised learning. As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning. As a target task, it can assess learned representation models in a uniform and interpretable manner. With VCP, we train spatial-temporal representation models (3D-CNNs) and apply such models on action recognition and video retrieval tasks. Experiments on commonly used benchmarks show that the trained models outperform the state-of-the-art self-supervised models with significant margins.","url_abs":"https://arxiv.org/abs/2001.00294v1","url_pdf":"https://arxiv.org/pdf/2001.00294v1.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":"video-cloze-procedure-for-self-supervised","repo_url":"https://github.com/BestJuly/VCP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"self-supervised-action-recognition","task_name":"Self-Supervised Action Recognition"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"self-supervised-video-retrieval","task_name":"Self-supervised Video Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","task":"Self-Supervised Action Recognition","dataset":"HMDB51","model":"VCP (R3D)","rank_in_archive_order":44,"of":48,"metrics":{"Frozen":"false","Pre-Training Dataset":"UCF101","Top-1 Accuracy":"31.5"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101","task":"Self-Supervised Action Recognition","dataset":"UCF101","model":"VCP (R3D)","rank_in_archive_order":41,"of":53,"metrics":{"3-fold Accuracy":"66","Frozen":"false","Pre-Training Dataset":"UCF101"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.00294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00294"}},"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/BestJuly/VCP","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":2},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"4974207d52f3cd18","entry":"adjacent_shuffle","repo":"BestJuly/VCP","repo_kind":"listed","path":"train_vcp.py","file_url":"https://github.com/BestJuly/VCP/blob/HEAD/train_vcp.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4974207d52f3cd18"}},{"code_sha256_prefix":"56662da192c79898","entry":"preprocess","repo":"BestJuly/VCP","repo_kind":"listed","path":"train_vcp.py","file_url":"https://github.com/BestJuly/VCP/blob/HEAD/train_vcp.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56662da192c79898"}},{"code_sha256_prefix":"beccd0c483c4762e","entry":"spatial_permutation","repo":"BestJuly/VCP","repo_kind":"listed","path":"train_vcp.py","file_url":"https://github.com/BestJuly/VCP/blob/HEAD/train_vcp.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"beccd0c483c4762e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}