{"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/unleash-the-potential-of-clip-for-video","title":"Unleash the Potential of CLIP for Video Highlight Detection","arxiv_id":"2404.01745","date":"2024-04-02","proceeding":null,"authors":["Donghoon Han","Seunghyeon Seo","Eunhwan Park","Seong-Uk Nam","Nojun Kwak"],"abstract":"Multimodal and large language models (LLMs) have revolutionized the utilization of open-world knowledge, unlocking novel potentials across various tasks and applications. Among these domains, the video domain has notably benefited from their capabilities. In this paper, we present Highlight-CLIP (HL-CLIP), a method designed to excel in the video highlight detection task by leveraging the pre-trained knowledge embedded in multimodal models. By simply fine-tuning the multimodal encoder in combination with our innovative saliency pooling technique, we have achieved the state-of-the-art performance in the highlight detection task, the QVHighlight Benchmark, to the best of our knowledge.","url_abs":"https://arxiv.org/abs/2404.01745v1","url_pdf":"https://arxiv.org/pdf/2404.01745v1.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":"unleash-the-potential-of-clip-for-video","repo_url":"https://github.com/dhk1349/HL-CLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"highlight-detection","task_name":"Highlight Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/highlight-detection-on-qvhighlights","task":"Highlight Detection","dataset":"QVHighlights","model":"HL-CLIP","rank_in_archive_order":5,"of":21,"metrics":{"Hit@1":"70.60","mAP":"41.94"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.01745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01745"}},"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/dhk1349/HL-CLIP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"dhk1349/HL-CLIP","repo_kind":"listed","path":"run_on_video/clip/simple_tokenizer.py","file_url":"https://github.com/dhk1349/HL-CLIP/blob/HEAD/run_on_video/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"dhk1349/HL-CLIP","repo_kind":"listed","path":"run_on_video/clip/simple_tokenizer.py","file_url":"https://github.com/dhk1349/HL-CLIP/blob/HEAD/run_on_video/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"dhk1349/HL-CLIP","repo_kind":"listed","path":"run_on_video/clip/simple_tokenizer.py","file_url":"https://github.com/dhk1349/HL-CLIP/blob/HEAD/run_on_video/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"ea50632a281cc0cd","entry":"build_model","repo":"dhk1349/HL-CLIP","repo_kind":"listed","path":"run_on_video/clip/model.py","file_url":"https://github.com/dhk1349/HL-CLIP/blob/HEAD/run_on_video/clip/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea50632a281cc0cd"}},{"code_sha256_prefix":"edb929dece68582e","entry":"count_parameters","repo":"dhk1349/HL-CLIP","repo_kind":"listed","path":"utils/model_utils.py","file_url":"https://github.com/dhk1349/HL-CLIP/blob/HEAD/utils/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"edb929dece68582e"}},{"code_sha256_prefix":"d27d456412e4f812","entry":"load","repo":"dhk1349/HL-CLIP","repo_kind":"listed","path":"run_on_video/clip/clip.py","file_url":"https://github.com/dhk1349/HL-CLIP/blob/HEAD/run_on_video/clip/clip.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d27d456412e4f812"}},{"code_sha256_prefix":"a82091666b9db8cf","entry":"multi_head_attention_forward","repo":"dhk1349/HL-CLIP","repo_kind":"listed","path":"moment_detr/attention.py","file_url":"https://github.com/dhk1349/HL-CLIP/blob/HEAD/moment_detr/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a82091666b9db8cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}