{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SP5YVLL7BE6DCKYYDMRRIJ2EE7","short_pith_number":"pith:SP5YVLL7","schema_version":"1.0","canonical_sha256":"93fb8aad7f093c312b181b2314274427cecbaa8eb24e12d1f9ab87cfc199286b","source":{"kind":"arxiv","id":"2301.07868","version":2},"attestation_state":"computed","paper":{"title":"MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Jiashi Feng, Kai Xu, Peng Wang, Weibo Gong, Xiaohui Shen, Xiaojie Jin, Xueqing Deng, Zhao Zhang","submitted_at":"2023-01-19T03:42:56Z","abstract_excerpt":"State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate model per task must be stored. To address this issue, we present our pioneering work that enables parameter-efficient VTR using a pre-trained model, with only a small number of tunable parameters during training. Towards this goal, we propose a new method dubbed Multimodal Video Adapter (MV-Adapter) for efficiently transferring the knowledge in the pre-trained C"},"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":"2301.07868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-19T03:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"d435bd6e518ba3aac9618eaaad751eee9067c0dc32e325d0eb50e0a0efeeaf56","abstract_canon_sha256":"25c1ac29c3b2a294958b1b0703b2feca546aaa7872f2574efa5f6677bd30b8a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:39.395975Z","signature_b64":"E9HhGiubw8UJpMCcCG6G3qYS9qEGdzgEeZNpM4MKHxGw1Kjm1QyOfJ2SFELmOYz4AsoHxifq04PIgh6nGl7JCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93fb8aad7f093c312b181b2314274427cecbaa8eb24e12d1f9ab87cfc199286b","last_reissued_at":"2026-07-05T08:06:39.395065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:39.395065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Jiashi Feng, Kai Xu, Peng Wang, Weibo Gong, Xiaohui Shen, Xiaojie Jin, Xueqing Deng, Zhao Zhang","submitted_at":"2023-01-19T03:42:56Z","abstract_excerpt":"State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate model per task must be stored. To address this issue, we present our pioneering work that enables parameter-efficient VTR using a pre-trained model, with only a small number of tunable parameters during training. Towards this goal, we propose a new method dubbed Multimodal Video Adapter (MV-Adapter) for efficiently transferring the knowledge in the pre-trained C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07868","kind":"arxiv","version":2},"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/2301.07868/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":"2301.07868","created_at":"2026-07-05T08:06:39.395490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.07868v2","created_at":"2026-07-05T08:06:39.395490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07868","created_at":"2026-07-05T08:06:39.395490+00:00"},{"alias_kind":"pith_short_12","alias_value":"SP5YVLL7BE6D","created_at":"2026-07-05T08:06:39.395490+00:00"},{"alias_kind":"pith_short_16","alias_value":"SP5YVLL7BE6DCKYY","created_at":"2026-07-05T08:06:39.395490+00:00"},{"alias_kind":"pith_short_8","alias_value":"SP5YVLL7","created_at":"2026-07-05T08:06:39.395490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.06950","citing_title":"READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2406.05615","citing_title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7","json":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7.json","graph_json":"https://pith.science/api/pith-number/SP5YVLL7BE6DCKYYDMRRIJ2EE7/graph.json","events_json":"https://pith.science/api/pith-number/SP5YVLL7BE6DCKYYDMRRIJ2EE7/events.json","paper":"https://pith.science/paper/SP5YVLL7"},"agent_actions":{"view_html":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7","download_json":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7.json","view_paper":"https://pith.science/paper/SP5YVLL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.07868&json=true","fetch_graph":"https://pith.science/api/pith-number/SP5YVLL7BE6DCKYYDMRRIJ2EE7/graph.json","fetch_events":"https://pith.science/api/pith-number/SP5YVLL7BE6DCKYYDMRRIJ2EE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/action/storage_attestation","attest_author":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/action/author_attestation","sign_citation":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/action/citation_signature","submit_replication":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/action/replication_record"}},"created_at":"2026-07-05T08:06:39.395490+00:00","updated_at":"2026-07-05T08:06:39.395490+00:00"}