{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QSHCC5CPOIWES5M4AAPV52BVMP","short_pith_number":"pith:QSHCC5CP","schema_version":"1.0","canonical_sha256":"848e21744f722c49759c001f5ee83563f98ac41172a44f52377119184517d38f","source":{"kind":"arxiv","id":"2212.03640","version":3},"attestation_state":"computed","paper":{"title":"Fine-tuned CLIP Models are Efficient Video Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","submitted_at":"2022-12-06T18:59:58Z","abstract_excerpt":"Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain. In this pursuit, new parametric modules are added to learn temporal information and inter-frame relationships which require meticulous design efforts. Furthermore, when the resulting models are learned on videos, they tend to overfit on the given task distribution and lack in generalization aspect. This begs the following question: How to effectiv"},"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":"2212.03640","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-06T18:59:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"869fc7e141102b38d98692aa1d6dfa856678f33f917a9120934685ede491095b","abstract_canon_sha256":"e1c9b4071e58d646b0c63f676ac02e92e33d08a2366857e72c50c6e88945b56c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:34.213822Z","signature_b64":"qW1AuIWiTTuq4iiUs9L+k3JWuix7TWW6ghWtOdYl31XAAxgLxjpNXubtLUL94zOFtJ5M2KnB5+RPWhPSK757Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"848e21744f722c49759c001f5ee83563f98ac41172a44f52377119184517d38f","last_reissued_at":"2026-07-05T05:54:34.213301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:34.213301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tuned CLIP Models are Efficient Video Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","submitted_at":"2022-12-06T18:59:58Z","abstract_excerpt":"Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain. In this pursuit, new parametric modules are added to learn temporal information and inter-frame relationships which require meticulous design efforts. Furthermore, when the resulting models are learned on videos, they tend to overfit on the given task distribution and lack in generalization aspect. This begs the following question: How to effectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03640","kind":"arxiv","version":3},"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/2212.03640/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":"2212.03640","created_at":"2026-07-05T05:54:34.213376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.03640v3","created_at":"2026-07-05T05:54:34.213376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03640","created_at":"2026-07-05T05:54:34.213376+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSHCC5CPOIWE","created_at":"2026-07-05T05:54:34.213376+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSHCC5CPOIWES5M4","created_at":"2026-07-05T05:54:34.213376+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSHCC5CP","created_at":"2026-07-05T05:54:34.213376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP","json":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP.json","graph_json":"https://pith.science/api/pith-number/QSHCC5CPOIWES5M4AAPV52BVMP/graph.json","events_json":"https://pith.science/api/pith-number/QSHCC5CPOIWES5M4AAPV52BVMP/events.json","paper":"https://pith.science/paper/QSHCC5CP"},"agent_actions":{"view_html":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP","download_json":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP.json","view_paper":"https://pith.science/paper/QSHCC5CP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.03640&json=true","fetch_graph":"https://pith.science/api/pith-number/QSHCC5CPOIWES5M4AAPV52BVMP/graph.json","fetch_events":"https://pith.science/api/pith-number/QSHCC5CPOIWES5M4AAPV52BVMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP/action/storage_attestation","attest_author":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP/action/author_attestation","sign_citation":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP/action/citation_signature","submit_replication":"https://pith.science/pith/QSHCC5CPOIWES5M4AAPV52BVMP/action/replication_record"}},"created_at":"2026-07-05T05:54:34.213376+00:00","updated_at":"2026-07-05T05:54:34.213376+00:00"}