{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K3QLGRWC75CYAIXEDAYAE7CDKB","short_pith_number":"pith:K3QLGRWC","schema_version":"1.0","canonical_sha256":"56e0b346c2ff458022e41830027c435061668e3fafab88a07f6da7b79ec64353","source":{"kind":"arxiv","id":"2209.06430","version":4},"attestation_state":"computed","paper":{"title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Hongwei Xue, Houqiang Li, Jianlong Fu, Jiebo Luo, Ruihua Song, Yuchong Sun","submitted_at":"2022-09-14T05:47:02Z","abstract_excerpt":"The pre-trained image-text models, like CLIP, have demonstrated the strong power of vision-language representation learned from a large scale of web-collected image-text data. In light of the well-learned visual features, some existing works transfer image representation to video domain and achieve good results. However, how to utilize image-language pre-trained model (e.g., CLIP) for video-language pre-training (post-pretraining) is still under explored. In this paper, we investigate two questions: 1) what are the factors hindering post-pretraining CLIP to further improve the performance on v"},"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":"2209.06430","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T05:47:02Z","cross_cats_sorted":[],"title_canon_sha256":"928664b4d66dca04730b0e3d42ef229772f5ef68d9808105184efbf830311846","abstract_canon_sha256":"afeeb423b79716bf6f62f1605369b8a243f897d1b39e979bc82eae875c886e50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:17.452570Z","signature_b64":"XJ1/4jMdseNTfWO0XoM41ASv6yP9hjUqWpKvRXwhSnDZFEb+prauYmvCP31joLf0GQ9feTPtNyxIClG1hYYrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56e0b346c2ff458022e41830027c435061668e3fafab88a07f6da7b79ec64353","last_reissued_at":"2026-07-05T05:47:17.452105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:17.452105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Hongwei Xue, Houqiang Li, Jianlong Fu, Jiebo Luo, Ruihua Song, Yuchong Sun","submitted_at":"2022-09-14T05:47:02Z","abstract_excerpt":"The pre-trained image-text models, like CLIP, have demonstrated the strong power of vision-language representation learned from a large scale of web-collected image-text data. In light of the well-learned visual features, some existing works transfer image representation to video domain and achieve good results. However, how to utilize image-language pre-trained model (e.g., CLIP) for video-language pre-training (post-pretraining) is still under explored. In this paper, we investigate two questions: 1) what are the factors hindering post-pretraining CLIP to further improve the performance on v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06430","kind":"arxiv","version":4},"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/2209.06430/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":"2209.06430","created_at":"2026-07-05T05:47:17.452163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06430v4","created_at":"2026-07-05T05:47:17.452163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06430","created_at":"2026-07-05T05:47:17.452163+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3QLGRWC75CY","created_at":"2026-07-05T05:47:17.452163+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3QLGRWC75CYAIXE","created_at":"2026-07-05T05:47:17.452163+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3QLGRWC","created_at":"2026-07-05T05:47:17.452163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00446","citing_title":"VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06964","citing_title":"Adversarial Video Promotion Against Text-to-Video Retrieval","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13511","citing_title":"Adapting MLLMs for Nuanced Video Retrieval","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB","json":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB.json","graph_json":"https://pith.science/api/pith-number/K3QLGRWC75CYAIXEDAYAE7CDKB/graph.json","events_json":"https://pith.science/api/pith-number/K3QLGRWC75CYAIXEDAYAE7CDKB/events.json","paper":"https://pith.science/paper/K3QLGRWC"},"agent_actions":{"view_html":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB","download_json":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB.json","view_paper":"https://pith.science/paper/K3QLGRWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06430&json=true","fetch_graph":"https://pith.science/api/pith-number/K3QLGRWC75CYAIXEDAYAE7CDKB/graph.json","fetch_events":"https://pith.science/api/pith-number/K3QLGRWC75CYAIXEDAYAE7CDKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/action/storage_attestation","attest_author":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/action/author_attestation","sign_citation":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/action/citation_signature","submit_replication":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/action/replication_record"}},"created_at":"2026-07-05T05:47:17.452163+00:00","updated_at":"2026-07-05T05:47:17.452163+00:00"}