{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DAQBVJJAA52X6UZXF2RUTLFIOQ","short_pith_number":"pith:DAQBVJJA","schema_version":"1.0","canonical_sha256":"18201aa52007757f53372ea349aca8740857f108b47ba9ec1e44030ec72bbcba","source":{"kind":"arxiv","id":"2401.17797","version":1},"attestation_state":"computed","paper":{"title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunluan Zhou, Ming Yang, Qingpei Guo, Xingning Dong, Xuzheng Yu, Zipeng Feng","submitted_at":"2024-01-31T12:45:44Z","abstract_excerpt":"We present a Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards effective and efficient zero-shot video-text retrieval, dubbed M2-RAAP. Upon popular image-text models like CLIP, most current adaptation-based video-text pre-training methods are confronted by three major issues, i.e., noisy data corpus, time-consuming pre-training, and limited performance gain. Towards this end, we conduct a comprehensive study including four critical steps in video-text pre-training. Specifically, we investigate 1) data filtering and refinement, 2) video input type selection, 3) temporal mod"},"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":"2401.17797","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T12:45:44Z","cross_cats_sorted":[],"title_canon_sha256":"9b049c70e89cf97bf03ed8602a16492958bd268d4c6c17a885a805803571774b","abstract_canon_sha256":"be2d01577eec47b7ce6cae70dca5a808ce73237be03d0c8a7d84449b5acaba98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:42.594247Z","signature_b64":"shcxPCqRQUslnlpZh5EC9uJSQ6RZHBOirqqaV/OZI4DJgdu7VQM2pXIHHBptFbGcBHMmTgZ/U4IGZ0OUV3KSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18201aa52007757f53372ea349aca8740857f108b47ba9ec1e44030ec72bbcba","last_reissued_at":"2026-07-05T07:39:42.593891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:42.593891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunluan Zhou, Ming Yang, Qingpei Guo, Xingning Dong, Xuzheng Yu, Zipeng Feng","submitted_at":"2024-01-31T12:45:44Z","abstract_excerpt":"We present a Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards effective and efficient zero-shot video-text retrieval, dubbed M2-RAAP. Upon popular image-text models like CLIP, most current adaptation-based video-text pre-training methods are confronted by three major issues, i.e., noisy data corpus, time-consuming pre-training, and limited performance gain. Towards this end, we conduct a comprehensive study including four critical steps in video-text pre-training. Specifically, we investigate 1) data filtering and refinement, 2) video input type selection, 3) temporal mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17797","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/2401.17797/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":"2401.17797","created_at":"2026-07-05T07:39:42.593956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17797v1","created_at":"2026-07-05T07:39:42.593956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17797","created_at":"2026-07-05T07:39:42.593956+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAQBVJJAA52X","created_at":"2026-07-05T07:39:42.593956+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAQBVJJAA52X6UZX","created_at":"2026-07-05T07:39:42.593956+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAQBVJJA","created_at":"2026-07-05T07:39:42.593956+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/DAQBVJJAA52X6UZXF2RUTLFIOQ","json":"https://pith.science/pith/DAQBVJJAA52X6UZXF2RUTLFIOQ.json","graph_json":"https://pith.science/api/pith-number/DAQBVJJAA52X6UZXF2RUTLFIOQ/graph.json","events_json":"https://pith.science/api/pith-number/DAQBVJJAA52X6UZXF2RUTLFIOQ/events.json","paper":"https://pith.science/paper/DAQBVJJA"},"agent_actions":{"view_html":"https://pith.science/pith/DAQBVJJAA52X6UZXF2RUTLFIOQ","download_json":"https://pith.science/pith/DAQBVJJAA52X6UZXF2RUTLFIOQ.json","view_paper":"https://pith.science/paper/DAQBVJJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17797&json=true","fetch_graph":"https://pith.science/api/pith-number/DAQBVJJAA52X6UZXF2RUTLFIOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DAQBVJJAA52X6UZXF2RUTLFIOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAQBVJJAA52X6UZXF2RUTLFIOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAQBVJJAA52X6UZXF2RUTLFIOQ/action/storage_attestation","attest_author":"https://pith.science/pith/DAQBVJJAA52X6UZXF2RUTLFIOQ/action/author_attestation","sign_citation":"https://pith.science/pith/DAQBVJJAA52X6UZXF2RUTLFIOQ/action/citation_signature","submit_replication":"https://pith.science/pith/DAQBVJJAA52X6UZXF2RUTLFIOQ/action/replication_record"}},"created_at":"2026-07-05T07:39:42.593956+00:00","updated_at":"2026-07-05T07:39:42.593956+00:00"}