{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6DGZ2E2ZS7FMH7XXBC4C37BB4D","short_pith_number":"pith:6DGZ2E2Z","schema_version":"1.0","canonical_sha256":"f0cd9d135997cac3fef708b82dfc21e0e8adb203ba3ecf36ce8bdffa977722aa","source":{"kind":"arxiv","id":"2404.01745","version":1},"attestation_state":"computed","paper":{"title":"Unleash the Potential of CLIP for Video Highlight Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Donghoon Han, Eunhwan Park, Nojun Kwak, Seong-Uk Nam, Seunghyeon Seo","submitted_at":"2024-04-02T09:01:58Z","abstract_excerpt":"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 performanc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.01745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T09:01:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"929f0750db7cbd7f77dd37a53d9b1bc2a2e3bc7bbc4a0bcc0322e8e33a3141b8","abstract_canon_sha256":"2091b910a838e14f2f3bab05195c384801afa694fcfcee9e24995eb94dc3190f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:19.022492Z","signature_b64":"uXPRiZoAFB8jSdZZ67nAdB7u9K6xKOmdU0FDxfnRFvC8STC3EvRf6JRvX7rChoklV3IWa8zlkWzM5RQqtmuGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0cd9d135997cac3fef708b82dfc21e0e8adb203ba3ecf36ce8bdffa977722aa","last_reissued_at":"2026-07-05T08:03:19.022128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:19.022128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleash the Potential of CLIP for Video Highlight Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Donghoon Han, Eunhwan Park, Nojun Kwak, Seong-Uk Nam, Seunghyeon Seo","submitted_at":"2024-04-02T09:01:58Z","abstract_excerpt":"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 performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01745","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.01745/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.01745","created_at":"2026-07-05T08:03:19.022187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01745v1","created_at":"2026-07-05T08:03:19.022187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01745","created_at":"2026-07-05T08:03:19.022187+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DGZ2E2ZS7FM","created_at":"2026-07-05T08:03:19.022187+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DGZ2E2ZS7FMH7XX","created_at":"2026-07-05T08:03:19.022187+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DGZ2E2Z","created_at":"2026-07-05T08:03:19.022187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07744","citing_title":"Sparse-Dense Side-Tuner for efficient Video Temporal Grounding","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D","json":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D.json","graph_json":"https://pith.science/api/pith-number/6DGZ2E2ZS7FMH7XXBC4C37BB4D/graph.json","events_json":"https://pith.science/api/pith-number/6DGZ2E2ZS7FMH7XXBC4C37BB4D/events.json","paper":"https://pith.science/paper/6DGZ2E2Z"},"agent_actions":{"view_html":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D","download_json":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D.json","view_paper":"https://pith.science/paper/6DGZ2E2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01745&json=true","fetch_graph":"https://pith.science/api/pith-number/6DGZ2E2ZS7FMH7XXBC4C37BB4D/graph.json","fetch_events":"https://pith.science/api/pith-number/6DGZ2E2ZS7FMH7XXBC4C37BB4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/action/storage_attestation","attest_author":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/action/author_attestation","sign_citation":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/action/citation_signature","submit_replication":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/action/replication_record"}},"created_at":"2026-07-05T08:03:19.022187+00:00","updated_at":"2026-07-05T08:03:19.022187+00:00"}