{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MRWVMQVFZAK6CWCETFYYZ7IDKV","short_pith_number":"pith:MRWVMQVF","schema_version":"1.0","canonical_sha256":"646d5642a5c815e1584499718cfd035575f1c8f342adfe82ed5cbf96bb16a851","source":{"kind":"arxiv","id":"2405.19465","version":1},"attestation_state":"computed","paper":{"title":"RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Ge Li, Haoran Tang, Jinfa Huang, Li Yuan, Long Chen, Meng Cao, Peng Jin, Ruyang Liu, Xiaodan Liang","submitted_at":"2024-05-29T19:23:53Z","abstract_excerpt":"Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most state-of-the-art TVR methods learn image-to-video transfer learning based on large-scale pre-trained visionlanguage models (e.g., CLIP). However, fully fine-tuning these pre-trained models for TVR incurs prohibitively expensive computation costs. To this end, we propose to conduct efficient text-video Retrieval with a sparse-andcorrelated AdaPter (RAP), i.e., fine-tuning the pre-trained model with a few parameterized layers. To accommodate the text-video scenario, we equip our RAP with "},"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":"2405.19465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T19:23:53Z","cross_cats_sorted":[],"title_canon_sha256":"2109292c5574a1b6560586a54ff35bac94b5ecb3bbc8267c1067a04244b0e12a","abstract_canon_sha256":"9c7f165cf5943c591d7ba2fbb22601ff9e8affcf4fbf265f84f18d4fa4240a9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:07.895012Z","signature_b64":"G4Xfvskw+uHYPSsLYGl73cvHI8tCJMp9QQ8+++9D6Glykg3aXQ+XRWg8a1zDma1gKGN1EioUchB9V9dvDzoWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"646d5642a5c815e1584499718cfd035575f1c8f342adfe82ed5cbf96bb16a851","last_reissued_at":"2026-07-05T08:25:07.894542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:07.894542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Ge Li, Haoran Tang, Jinfa Huang, Li Yuan, Long Chen, Meng Cao, Peng Jin, Ruyang Liu, Xiaodan Liang","submitted_at":"2024-05-29T19:23:53Z","abstract_excerpt":"Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most state-of-the-art TVR methods learn image-to-video transfer learning based on large-scale pre-trained visionlanguage models (e.g., CLIP). However, fully fine-tuning these pre-trained models for TVR incurs prohibitively expensive computation costs. To this end, we propose to conduct efficient text-video Retrieval with a sparse-andcorrelated AdaPter (RAP), i.e., fine-tuning the pre-trained model with a few parameterized layers. To accommodate the text-video scenario, we equip our RAP with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19465","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/2405.19465/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":"2405.19465","created_at":"2026-07-05T08:25:07.894593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19465v1","created_at":"2026-07-05T08:25:07.894593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19465","created_at":"2026-07-05T08:25:07.894593+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRWVMQVFZAK6","created_at":"2026-07-05T08:25:07.894593+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRWVMQVFZAK6CWCE","created_at":"2026-07-05T08:25:07.894593+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRWVMQVF","created_at":"2026-07-05T08:25:07.894593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19024","citing_title":"ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV","json":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV.json","graph_json":"https://pith.science/api/pith-number/MRWVMQVFZAK6CWCETFYYZ7IDKV/graph.json","events_json":"https://pith.science/api/pith-number/MRWVMQVFZAK6CWCETFYYZ7IDKV/events.json","paper":"https://pith.science/paper/MRWVMQVF"},"agent_actions":{"view_html":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV","download_json":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV.json","view_paper":"https://pith.science/paper/MRWVMQVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19465&json=true","fetch_graph":"https://pith.science/api/pith-number/MRWVMQVFZAK6CWCETFYYZ7IDKV/graph.json","fetch_events":"https://pith.science/api/pith-number/MRWVMQVFZAK6CWCETFYYZ7IDKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV/action/storage_attestation","attest_author":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV/action/author_attestation","sign_citation":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV/action/citation_signature","submit_replication":"https://pith.science/pith/MRWVMQVFZAK6CWCETFYYZ7IDKV/action/replication_record"}},"created_at":"2026-07-05T08:25:07.894593+00:00","updated_at":"2026-07-05T08:25:07.894593+00:00"}