{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:26ZMP2T6I574VIMCQHWMW3AT24","short_pith_number":"pith:26ZMP2T6","schema_version":"1.0","canonical_sha256":"d7b2c7ea7e477fcaa18281eccb6c13d719fcfa833cc389ff879383a6f5683261","source":{"kind":"arxiv","id":"2303.05313","version":2},"attestation_state":"computed","paper":{"title":"Refined Vision-Language Modeling for Fine-grained Multi-modal Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lisai Zhang, Qingcai Chen, Yunpeng Han, Zhao Cao, Zhijian Chen, Zhonghua Li","submitted_at":"2023-03-09T15:01:12Z","abstract_excerpt":"Fine-grained supervision based on object annotations has been widely used for vision and language pre-training (VLP). However, in real-world application scenarios, aligned multi-modal data is usually in the image-caption format, which only provides coarse-grained supervision. It is not only cost-expensive but also compute-expensive to collect object annotations and build object annotation pre-extractor for different scenarios. In this paper, we propose a fine-grained VLP scheme without object annotations from the linguistic perspective. First, we propose a homonym sentence rewriting (HSR) algo"},"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":"2303.05313","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-09T15:01:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f19ec871d73feadddce49e771b2b56dfda66d1f9f53ee2a366adcf582a85983d","abstract_canon_sha256":"7bc7e4669a47ffb1dc3beefc81e15710c8cbeda6864d6533fc4727ce844b2163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:37.663567Z","signature_b64":"82VymKdRazgdvCxffA/5ytS1Ze64Yo7L6Gh3X/8dUj8M1gurMr+ob/PbZGFDXYwhWCXjS7GbSkXGEvvCHWkuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7b2c7ea7e477fcaa18281eccb6c13d719fcfa833cc389ff879383a6f5683261","last_reissued_at":"2026-07-05T06:07:37.663027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:37.663027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refined Vision-Language Modeling for Fine-grained Multi-modal Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lisai Zhang, Qingcai Chen, Yunpeng Han, Zhao Cao, Zhijian Chen, Zhonghua Li","submitted_at":"2023-03-09T15:01:12Z","abstract_excerpt":"Fine-grained supervision based on object annotations has been widely used for vision and language pre-training (VLP). However, in real-world application scenarios, aligned multi-modal data is usually in the image-caption format, which only provides coarse-grained supervision. It is not only cost-expensive but also compute-expensive to collect object annotations and build object annotation pre-extractor for different scenarios. In this paper, we propose a fine-grained VLP scheme without object annotations from the linguistic perspective. First, we propose a homonym sentence rewriting (HSR) algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05313","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/2303.05313/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":"2303.05313","created_at":"2026-07-05T06:07:37.663165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05313v2","created_at":"2026-07-05T06:07:37.663165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05313","created_at":"2026-07-05T06:07:37.663165+00:00"},{"alias_kind":"pith_short_12","alias_value":"26ZMP2T6I574","created_at":"2026-07-05T06:07:37.663165+00:00"},{"alias_kind":"pith_short_16","alias_value":"26ZMP2T6I574VIMC","created_at":"2026-07-05T06:07:37.663165+00:00"},{"alias_kind":"pith_short_8","alias_value":"26ZMP2T6","created_at":"2026-07-05T06:07:37.663165+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/26ZMP2T6I574VIMCQHWMW3AT24","json":"https://pith.science/pith/26ZMP2T6I574VIMCQHWMW3AT24.json","graph_json":"https://pith.science/api/pith-number/26ZMP2T6I574VIMCQHWMW3AT24/graph.json","events_json":"https://pith.science/api/pith-number/26ZMP2T6I574VIMCQHWMW3AT24/events.json","paper":"https://pith.science/paper/26ZMP2T6"},"agent_actions":{"view_html":"https://pith.science/pith/26ZMP2T6I574VIMCQHWMW3AT24","download_json":"https://pith.science/pith/26ZMP2T6I574VIMCQHWMW3AT24.json","view_paper":"https://pith.science/paper/26ZMP2T6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05313&json=true","fetch_graph":"https://pith.science/api/pith-number/26ZMP2T6I574VIMCQHWMW3AT24/graph.json","fetch_events":"https://pith.science/api/pith-number/26ZMP2T6I574VIMCQHWMW3AT24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26ZMP2T6I574VIMCQHWMW3AT24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26ZMP2T6I574VIMCQHWMW3AT24/action/storage_attestation","attest_author":"https://pith.science/pith/26ZMP2T6I574VIMCQHWMW3AT24/action/author_attestation","sign_citation":"https://pith.science/pith/26ZMP2T6I574VIMCQHWMW3AT24/action/citation_signature","submit_replication":"https://pith.science/pith/26ZMP2T6I574VIMCQHWMW3AT24/action/replication_record"}},"created_at":"2026-07-05T06:07:37.663165+00:00","updated_at":"2026-07-05T06:07:37.663165+00:00"}