{"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/leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","arxiv_id":"2404.09490","date":"2024-04-15","proceeding":null,"authors":["Minji Kim","Dongyoon Han","Taekyung Kim","Bohyung Han"],"abstract":"We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we introduce Temporal Contextualization (TC), a layer-wise temporal information infusion mechanism for videos, which 1) extracts core information from each frame, 2) connects relevant information across frames for the summarization into context tokens, and 3) leverages the context tokens for feature encoding. Furthermore, the Video-conditional Prompting (VP) module processes context tokens to generate informative prompts in the text modality. Extensive experiments in zero-shot, few-shot, base-to-novel, and fully-supervised action recognition validate the effectiveness of our model. Ablation studies for TC and VP support our design choices. Our project page with the source code is available at https://github.com/naver-ai/tc-clip","url_abs":"https://arxiv.org/abs/2404.09490v2","url_pdf":"https://arxiv.org/pdf/2404.09490v2.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":"leveraging-temporal-contextualization-for","repo_url":"https://github.com/naver-ai/tc-clip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"leveraging-temporal-contextualization-for","repo_url":"https://github.com/naver-ai/dawin","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":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-action-recognition-on-hmdb51","task":"Zero-Shot Action Recognition","dataset":"HMDB51","model":"TC-CLIP","rank_in_archive_order":8,"of":29,"metrics":{"Top-1 Accuracy":"56.0"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-kinetics","task":"Zero-Shot Action Recognition","dataset":"Kinetics","model":"TC-CLIP","rank_in_archive_order":1,"of":20,"metrics":{"Top-1 Accuracy":"78.1","Top-5 Accuracy":"95.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","task":"Zero-Shot Action Recognition","dataset":"UCF101","model":"TC-CLIP","rank_in_archive_order":7,"of":35,"metrics":{"Top-1 Accuracy":"85.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.09490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09490"}},"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":"deterministic:regex_extraction","url":"https://github.com/naver-ai/tc-clip","reach":null}],"summary":{"ran_fixture":1,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":4,"samples":[{"code_sha256_prefix":"84cccfdd563db842","entry":"bipartite_soft_matching","repo":"naver-ai/tc-clip","repo_kind":"official","path":"clip/transformer_blocks_tc.py","file_url":"https://github.com/naver-ai/tc-clip/blob/HEAD/clip/transformer_blocks_tc.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"84cccfdd563db842"}},{"code_sha256_prefix":"a2a8808a12641926","entry":"schedule_r_constant","repo":"naver-ai/tc-clip","repo_kind":"official","path":"clip/transformer_blocks_tc.py","file_url":"https://github.com/naver-ai/tc-clip/blob/HEAD/clip/transformer_blocks_tc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a2a8808a12641926"}},{"code_sha256_prefix":"c67f627bf7ead153","entry":"TCAttention","repo":"naver-ai/tc-clip","repo_kind":"official","path":"clip/transformer_blocks_tc.py","file_url":"https://github.com/naver-ai/tc-clip/blob/HEAD/clip/transformer_blocks_tc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c67f627bf7ead153"}},{"code_sha256_prefix":"b3c158ec52e5b8cf","entry":"TCAttentionBlock","repo":"naver-ai/tc-clip","repo_kind":"official","path":"clip/transformer_blocks_tc.py","file_url":"https://github.com/naver-ai/tc-clip/blob/HEAD/clip/transformer_blocks_tc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b3c158ec52e5b8cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}