{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2LBBF4VZVIC25NWABG4RAT7EAM","short_pith_number":"pith:2LBBF4VZ","schema_version":"1.0","canonical_sha256":"d2c212f2b9aa05aeb6c009b9104fe40315dc54fe8bf55dbea56a68cb7af8a53c","source":{"kind":"arxiv","id":"2310.16667","version":1},"attestation_state":"computed","paper":{"title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuofan Ma, Xiaojuan Qi, Xin Wen, Yi Jiang, Zehuan Yuan","submitted_at":"2023-10-25T14:31:02Z","abstract_excerpt":"Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self-trained vision-language models for alignment, which are prone to limitations in localization accuracy or generalization capabilities. In this paper, we propose CoDet, a novel approach that overcomes the reliance on pre-aligned vision-language space by reformulating region-word alignment as a co-occurring object discovery problem. Intuitively, by grouping images that mention a "},"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":"2310.16667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"fc3eed064fc942f3d7f5a69dde26e6810b50b59815605d8bab8f1d59a1089eaf","abstract_canon_sha256":"bff5a5c201a673c23373e11307982371f8c3008a949dfb43f9dc53d07c02db6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:01.037501Z","signature_b64":"E2Ie4pXSSgEdZRJvH3DdORBirUnMQYzebgwBJmcFhs8ZsnM3OWd1MmxXcHuQWcmpcD//l+OgnW5f1lahZZQVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2c212f2b9aa05aeb6c009b9104fe40315dc54fe8bf55dbea56a68cb7af8a53c","last_reissued_at":"2026-07-05T07:05:01.037012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:01.037012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuofan Ma, Xiaojuan Qi, Xin Wen, Yi Jiang, Zehuan Yuan","submitted_at":"2023-10-25T14:31:02Z","abstract_excerpt":"Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self-trained vision-language models for alignment, which are prone to limitations in localization accuracy or generalization capabilities. In this paper, we propose CoDet, a novel approach that overcomes the reliance on pre-aligned vision-language space by reformulating region-word alignment as a co-occurring object discovery problem. Intuitively, by grouping images that mention a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16667","kind":"arxiv","version":1},"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/2310.16667/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":"2310.16667","created_at":"2026-07-05T07:05:01.037066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16667v1","created_at":"2026-07-05T07:05:01.037066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16667","created_at":"2026-07-05T07:05:01.037066+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LBBF4VZVIC2","created_at":"2026-07-05T07:05:01.037066+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LBBF4VZVIC25NWA","created_at":"2026-07-05T07:05:01.037066+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LBBF4VZ","created_at":"2026-07-05T07:05:01.037066+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/2LBBF4VZVIC25NWABG4RAT7EAM","json":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM.json","graph_json":"https://pith.science/api/pith-number/2LBBF4VZVIC25NWABG4RAT7EAM/graph.json","events_json":"https://pith.science/api/pith-number/2LBBF4VZVIC25NWABG4RAT7EAM/events.json","paper":"https://pith.science/paper/2LBBF4VZ"},"agent_actions":{"view_html":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM","download_json":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM.json","view_paper":"https://pith.science/paper/2LBBF4VZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16667&json=true","fetch_graph":"https://pith.science/api/pith-number/2LBBF4VZVIC25NWABG4RAT7EAM/graph.json","fetch_events":"https://pith.science/api/pith-number/2LBBF4VZVIC25NWABG4RAT7EAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/action/storage_attestation","attest_author":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/action/author_attestation","sign_citation":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/action/citation_signature","submit_replication":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/action/replication_record"}},"created_at":"2026-07-05T07:05:01.037066+00:00","updated_at":"2026-07-05T07:05:01.037066+00:00"}