{"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/static-and-dynamic-concepts-for-self","title":"Static and Dynamic Concepts for Self-supervised Video Representation Learning","arxiv_id":"2207.12795","date":"2022-07-26","proceeding":null,"authors":["Rui Qian","Shuangrui Ding","Xian Liu","Dahua Lin"],"abstract":"In this paper, we propose a novel learning scheme for self-supervised video representation learning. Motivated by how humans understand videos, we propose to first learn general visual concepts then attend to discriminative local areas for video understanding. Specifically, we utilize static frame and frame difference to help decouple static and dynamic concepts, and respectively align the concept distributions in latent space. We add diversity and fidelity regularizations to guarantee that we learn a compact set of meaningful concepts. Then we employ a cross-attention mechanism to aggregate detailed local features of different concepts, and filter out redundant concepts with low activations to perform local concept contrast. Extensive experiments demonstrate that our method distills meaningful static and dynamic concepts to guide video understanding, and obtains state-of-the-art results on UCF-101, HMDB-51, and Diving-48.","url_abs":"https://arxiv.org/abs/2207.12795v1","url_pdf":"https://arxiv.org/pdf/2207.12795v1.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":"static-and-dynamic-concepts-for-self","repo_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.12795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12795"}},"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/shvdiwnkozbw/Self-supervised-Video-Concept","reach":null}],"summary":{"ran":6,"ran_draft_wrong":2,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":11,"ran":9,"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":11,"samples":[{"code_sha256_prefix":"c4ad477562041329","entry":"BasicBlock","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c4ad477562041329"}},{"code_sha256_prefix":"3a790dd1ff8333e6","entry":"Bottleneck","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a790dd1ff8333e6"}},{"code_sha256_prefix":"a5a9e321d7c014d1","entry":"Conv2Plus1D","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a5a9e321d7c014d1"}},{"code_sha256_prefix":"7020be28ccab7107","entry":"LocalfeatureIntegrationTransformer","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7020be28ccab7107"}},{"code_sha256_prefix":"cead4e5aa4d8a2ce","entry":"R2Plus1dStem","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cead4e5aa4d8a2ce"}},{"code_sha256_prefix":"98f7f5b9fe4cf0e1","entry":"VideoResNet","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98f7f5b9fe4cf0e1"}},{"code_sha256_prefix":"4406f5d41311c04c","entry":"_video_resnet","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4406f5d41311c04c"}},{"code_sha256_prefix":"0a5f3a7a2114f2e2","entry":"shoot_infs","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0a5f3a7a2114f2e2"}},{"code_sha256_prefix":"ede20b10087a299b","entry":"sinkhorn","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ede20b10087a299b"}},{"code_sha256_prefix":"a87cee1a84b9f40e","entry":"GreatModel","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a87cee1a84b9f40e"}},{"code_sha256_prefix":"9388dbfda27300fa","entry":"r2plus1d_18","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","repo_kind":"official","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9388dbfda27300fa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}