{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RKDIN7TP5XZ4ROVED5HA3PHO5C","short_pith_number":"pith:RKDIN7TP","schema_version":"1.0","canonical_sha256":"8a8686fe6fedf3c8baa41f4e0dbceee8a8dcecfbe2e0a531213e64fd7a1d4e83","source":{"kind":"arxiv","id":"2004.06165","version":5},"attestation_state":"computed","paper":{"title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Furu Wei, Houdong Hu, Jianfeng Gao, Lei Zhang, Li Dong, Lijuan Wang, Pengchuan Zhang, Xiaowei Hu, Xiujun Li, Xi Yin, Yejin Choi","submitted_at":"2020-04-13T19:18:10Z","abstract_excerpt":"Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be pre-trained and use self-attention to learn image-text semantic alignments in a brute force manner, in this paper, we propose a new learning method Oscar (Object-Semantics Aligned Pre-training), which uses object tags detected in images as anchor points to significantly ease the learning of alignments. Our method is motivated by the observation th"},"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":"2004.06165","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T19:18:10Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"62d6643e8e62c662afbae0a66fb29bb2b65965ce3f646c5893c5c87761719271","abstract_canon_sha256":"157b99e4c8fd7baab864289c92502666c9ad2ed3d21bda5d6e9f2c1f32e2ec0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:01.393373Z","signature_b64":"b1gbYoBGoXdHGZn7tep1O2Q6uf/1d0jX2CcvubKWu+agGp2A3YgZjkbfaxevdqhRnbanb4WYQEGakQBLCeuJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a8686fe6fedf3c8baa41f4e0dbceee8a8dcecfbe2e0a531213e64fd7a1d4e83","last_reissued_at":"2026-07-05T01:22:01.392867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:01.392867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Furu Wei, Houdong Hu, Jianfeng Gao, Lei Zhang, Li Dong, Lijuan Wang, Pengchuan Zhang, Xiaowei Hu, Xiujun Li, Xi Yin, Yejin Choi","submitted_at":"2020-04-13T19:18:10Z","abstract_excerpt":"Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be pre-trained and use self-attention to learn image-text semantic alignments in a brute force manner, in this paper, we propose a new learning method Oscar (Object-Semantics Aligned Pre-training), which uses object tags detected in images as anchor points to significantly ease the learning of alignments. Our method is motivated by the observation th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06165","kind":"arxiv","version":5},"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/2004.06165/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":"2004.06165","created_at":"2026-07-05T01:22:01.392927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.06165v5","created_at":"2026-07-05T01:22:01.392927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06165","created_at":"2026-07-05T01:22:01.392927+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKDIN7TP5XZ4","created_at":"2026-07-05T01:22:01.392927+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKDIN7TP5XZ4ROVE","created_at":"2026-07-05T01:22:01.392927+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKDIN7TP","created_at":"2026-07-05T01:22:01.392927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.04427","citing_title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C","json":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C.json","graph_json":"https://pith.science/api/pith-number/RKDIN7TP5XZ4ROVED5HA3PHO5C/graph.json","events_json":"https://pith.science/api/pith-number/RKDIN7TP5XZ4ROVED5HA3PHO5C/events.json","paper":"https://pith.science/paper/RKDIN7TP"},"agent_actions":{"view_html":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C","download_json":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C.json","view_paper":"https://pith.science/paper/RKDIN7TP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.06165&json=true","fetch_graph":"https://pith.science/api/pith-number/RKDIN7TP5XZ4ROVED5HA3PHO5C/graph.json","fetch_events":"https://pith.science/api/pith-number/RKDIN7TP5XZ4ROVED5HA3PHO5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/action/storage_attestation","attest_author":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/action/author_attestation","sign_citation":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/action/citation_signature","submit_replication":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/action/replication_record"}},"created_at":"2026-07-05T01:22:01.392927+00:00","updated_at":"2026-07-05T01:22:01.392927+00:00"}