{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TI7HPQGMBMYGYKI2WOG436P3YI","short_pith_number":"pith:TI7HPQGM","schema_version":"1.0","canonical_sha256":"9a3e77c0cc0b306c291ab38dcdf9fbc20b99c997cc3fd85d3f5c29001b75b0e4","source":{"kind":"arxiv","id":"2204.07441","version":2},"attestation_state":"computed","paper":{"title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Haoyu Lu, Ji-Rong Wen, Nanyi Fei, Yizhao Gao, Yuqi Huo, Zhiwu Lu","submitted_at":"2022-04-15T12:34:47Z","abstract_excerpt":"Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high inference efficiency have also shown promising performance, however, they only consider instance-level alignment between the two streams (thus there is still room for improvement). To overcome these limitations, we propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval by enhancing cross-modal interaction. In "},"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":"2204.07441","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-15T12:34:47Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"ea47934e9885a0c3b47c9a0a9106bfac2603aafb0eb76ac040c25dfc649c21b8","abstract_canon_sha256":"b6eb2f912fec8d8b1426944a6ce9906c1e23f858acdd83a9ef208e2ae9d06968"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:59.223492Z","signature_b64":"rFK22PglZ00uJe3a65xgsE+W3nbZqrpCf4IM3eH0SUAITPEskQWKX3J/Jau6MQFqMLpRSS+oQai04L4PngNfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a3e77c0cc0b306c291ab38dcdf9fbc20b99c997cc3fd85d3f5c29001b75b0e4","last_reissued_at":"2026-07-05T04:24:59.223063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:59.223063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Haoyu Lu, Ji-Rong Wen, Nanyi Fei, Yizhao Gao, Yuqi Huo, Zhiwu Lu","submitted_at":"2022-04-15T12:34:47Z","abstract_excerpt":"Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high inference efficiency have also shown promising performance, however, they only consider instance-level alignment between the two streams (thus there is still room for improvement). To overcome these limitations, we propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval by enhancing cross-modal interaction. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07441","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/2204.07441/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":"2204.07441","created_at":"2026-07-05T04:24:59.223122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.07441v2","created_at":"2026-07-05T04:24:59.223122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07441","created_at":"2026-07-05T04:24:59.223122+00:00"},{"alias_kind":"pith_short_12","alias_value":"TI7HPQGMBMYG","created_at":"2026-07-05T04:24:59.223122+00:00"},{"alias_kind":"pith_short_16","alias_value":"TI7HPQGMBMYGYKI2","created_at":"2026-07-05T04:24:59.223122+00:00"},{"alias_kind":"pith_short_8","alias_value":"TI7HPQGM","created_at":"2026-07-05T04:24:59.223122+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/TI7HPQGMBMYGYKI2WOG436P3YI","json":"https://pith.science/pith/TI7HPQGMBMYGYKI2WOG436P3YI.json","graph_json":"https://pith.science/api/pith-number/TI7HPQGMBMYGYKI2WOG436P3YI/graph.json","events_json":"https://pith.science/api/pith-number/TI7HPQGMBMYGYKI2WOG436P3YI/events.json","paper":"https://pith.science/paper/TI7HPQGM"},"agent_actions":{"view_html":"https://pith.science/pith/TI7HPQGMBMYGYKI2WOG436P3YI","download_json":"https://pith.science/pith/TI7HPQGMBMYGYKI2WOG436P3YI.json","view_paper":"https://pith.science/paper/TI7HPQGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.07441&json=true","fetch_graph":"https://pith.science/api/pith-number/TI7HPQGMBMYGYKI2WOG436P3YI/graph.json","fetch_events":"https://pith.science/api/pith-number/TI7HPQGMBMYGYKI2WOG436P3YI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TI7HPQGMBMYGYKI2WOG436P3YI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TI7HPQGMBMYGYKI2WOG436P3YI/action/storage_attestation","attest_author":"https://pith.science/pith/TI7HPQGMBMYGYKI2WOG436P3YI/action/author_attestation","sign_citation":"https://pith.science/pith/TI7HPQGMBMYGYKI2WOG436P3YI/action/citation_signature","submit_replication":"https://pith.science/pith/TI7HPQGMBMYGYKI2WOG436P3YI/action/replication_record"}},"created_at":"2026-07-05T04:24:59.223122+00:00","updated_at":"2026-07-05T04:24:59.223122+00:00"}