{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AXZMJVULAWD32ITFG76W5ATZC4","short_pith_number":"pith:AXZMJVUL","schema_version":"1.0","canonical_sha256":"05f2c4d68b0587bd226537fd6e827917344f4e1c96e097acb2a104be3fb10658","source":{"kind":"arxiv","id":"2211.09623","version":2},"attestation_state":"computed","paper":{"title":"Cross-Modal Adapter for Vision-Language Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunjiang Ge, Gao Huang, Haojun Jiang, Jianke Zhang, Rui Huang, Shiji Song, Zanlin Ni","submitted_at":"2022-11-17T16:15:30Z","abstract_excerpt":"Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval tasks. However, as pre-trained models are scaling up, fully fine-tuning them on donwstream retrieval datasets has a high risk of overfitting. Moreover, in practice, it would be costly to train and store a large model for each task. To overcome the above issues, we present a novel Cross-Modal Adapter for parameter-efficient transfer learning. Inspired by adapter-b"},"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":"2211.09623","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T16:15:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"192d0cc969c69ddf2f89df5becda016b9b1bdd77919decbd00cf3d8e1d54f37c","abstract_canon_sha256":"6dc2e32c8d5c7ff21671e9c9ae3d824b6c935cdd1eed77997252349229d2fde4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:51.817977Z","signature_b64":"u7vZO0mI45tLV3P3OdgCjUCKEvpMScSu1LRCmBdfSO0E5AqbvZPMOFUSQtw0Ah3mY4fQMGC4KL5eK7KF5kl3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f2c4d68b0587bd226537fd6e827917344f4e1c96e097acb2a104be3fb10658","last_reissued_at":"2026-07-05T12:01:51.817505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:51.817505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Adapter for Vision-Language Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunjiang Ge, Gao Huang, Haojun Jiang, Jianke Zhang, Rui Huang, Shiji Song, Zanlin Ni","submitted_at":"2022-11-17T16:15:30Z","abstract_excerpt":"Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval tasks. However, as pre-trained models are scaling up, fully fine-tuning them on donwstream retrieval datasets has a high risk of overfitting. Moreover, in practice, it would be costly to train and store a large model for each task. To overcome the above issues, we present a novel Cross-Modal Adapter for parameter-efficient transfer learning. Inspired by adapter-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09623","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/2211.09623/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":"2211.09623","created_at":"2026-07-05T12:01:51.817564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09623v2","created_at":"2026-07-05T12:01:51.817564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09623","created_at":"2026-07-05T12:01:51.817564+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXZMJVULAWD3","created_at":"2026-07-05T12:01:51.817564+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXZMJVULAWD32ITF","created_at":"2026-07-05T12:01:51.817564+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXZMJVUL","created_at":"2026-07-05T12:01:51.817564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2401.07669","citing_title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00434","citing_title":"LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4","json":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4.json","graph_json":"https://pith.science/api/pith-number/AXZMJVULAWD32ITFG76W5ATZC4/graph.json","events_json":"https://pith.science/api/pith-number/AXZMJVULAWD32ITFG76W5ATZC4/events.json","paper":"https://pith.science/paper/AXZMJVUL"},"agent_actions":{"view_html":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4","download_json":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4.json","view_paper":"https://pith.science/paper/AXZMJVUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09623&json=true","fetch_graph":"https://pith.science/api/pith-number/AXZMJVULAWD32ITFG76W5ATZC4/graph.json","fetch_events":"https://pith.science/api/pith-number/AXZMJVULAWD32ITFG76W5ATZC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4/action/storage_attestation","attest_author":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4/action/author_attestation","sign_citation":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4/action/citation_signature","submit_replication":"https://pith.science/pith/AXZMJVULAWD32ITFG76W5ATZC4/action/replication_record"}},"created_at":"2026-07-05T12:01:51.817564+00:00","updated_at":"2026-07-05T12:01:51.817564+00:00"}