{"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/watch-video-catch-keyword-context-aware","title":"Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection","arxiv_id":"2501.02504","date":"2025-01-05","proceeding":null,"authors":["Sung Jin Um","DongJin Kim","Sangmin Lee","Jung Uk Kim"],"abstract":"The goal of video moment retrieval and highlight detection is to identify specific segments and highlights based on a given text query. With the rapid growth of video content and the overlap between these tasks, recent works have addressed both simultaneously. However, they still struggle to fully capture the overall video context, making it challenging to determine which words are most relevant. In this paper, we present a novel Video Context-aware Keyword Attention module that overcomes this limitation by capturing keyword variation within the context of the entire video. To achieve this, we introduce a video context clustering module that provides concise representations of the overall video context, thereby enhancing the understanding of keyword dynamics. Furthermore, we propose a keyword weight detection module with keyword-aware contrastive learning that incorporates keyword information to enhance fine-grained alignment between visual and textual features. Extensive experiments on the QVHighlights, TVSum, and Charades-STA benchmarks demonstrate that our proposed method significantly improves performance in moment retrieval and highlight detection tasks compared to existing approaches. Our code is available at: https://github.com/VisualAIKHU/Keyword-DETR","url_abs":"https://arxiv.org/abs/2501.02504v1","url_pdf":"https://arxiv.org/pdf/2501.02504v1.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":"watch-video-catch-keyword-context-aware","repo_url":"https://github.com/visualaikhu/keyword-detr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"highlight-detection","task_name":"Highlight Detection"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.02504","atlas_url":"https://app.syntology.ai/?focus=2501.02504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.02504"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/visualaikhu/keyword-detr","reach":null}],"summary":{"ran_fixture":6,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":10,"samples":[{"code_sha256_prefix":"a5491be770764e99","entry":"FINCH","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a5491be770764e99"}},{"code_sha256_prefix":"5bd0c943cf39930a","entry":"clust_rank","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5bd0c943cf39930a"}},{"code_sha256_prefix":"a01b4dae82c605b3","entry":"connected_components","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a01b4dae82c605b3"}},{"code_sha256_prefix":"6d57d0d9f47ab9ac","entry":"cool_mean","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d57d0d9f47ab9ac"}},{"code_sha256_prefix":"4fdea7107027864f","entry":"get_clust","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4fdea7107027864f"}},{"code_sha256_prefix":"56c72fe8bbeadae8","entry":"get_merge","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56c72fe8bbeadae8"}},{"code_sha256_prefix":"732d646a00f52bf8","entry":"pairwise_distances","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"732d646a00f52bf8"}},{"code_sha256_prefix":"6abe6f21a2d60d53","entry":"req_numclust","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6abe6f21a2d60d53"}},{"code_sha256_prefix":"8dd53619c5c0df78","entry":"KeywordWeighting","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.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":"8dd53619c5c0df78"}},{"code_sha256_prefix":"3e1ae56847475e08","entry":"update_adj","repo":"visualaikhu/keyword-detr","repo_kind":"official","path":"keyword_detr/keyword_attention.py","file_url":"https://github.com/visualaikhu/keyword-detr/blob/HEAD/keyword_detr/keyword_attention.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":"3e1ae56847475e08"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}