{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XYL5LWMRRK3JDLOUGE5MA4QX2Y","short_pith_number":"pith:XYL5LWMR","schema_version":"1.0","canonical_sha256":"be17d5d9918ab691add4313ac07217d6323a2c7bc8e096b7146419423fa4155e","source":{"kind":"arxiv","id":"2310.00161","version":2},"attestation_state":"computed","paper":{"title":"Region-centric Image-Language Pretraining for Open-Vocabulary Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anelia Angelova, Dahun Kim, Weicheng Kuo","submitted_at":"2023-09-29T21:56:37Z","abstract_excerpt":"We present a new open-vocabulary detection approach based on region-centric image-language pretraining to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we incorporate the detector architecture on top of the classification backbone, which better serves the region-level recognition needs of detection by enabling the detector heads to learn from large-scale image-text pairs. Using only standard contrastive loss and no pseudo-labeling, our approach is a simple yet effective extension of the contrastive learning method to learn emerge"},"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":"2310.00161","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T21:56:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0100f80b672efe89c37bc03c1b47660a329e602e51be8e5469af14b6fafd83e7","abstract_canon_sha256":"bb7f3b9bb741c42a335666a600e71196c457b2ecedefb2101a4ce08562b2d71f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:46.732782Z","signature_b64":"3TG9/jaG3Q22tNyPqCMbGDLOJW2MUr6PJZS8U6uAWHa+Lwl85P0HBPbUXcal2ufEjrqireX8j38RGPjRb6yGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be17d5d9918ab691add4313ac07217d6323a2c7bc8e096b7146419423fa4155e","last_reissued_at":"2026-07-05T08:45:46.732265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:46.732265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Region-centric Image-Language Pretraining for Open-Vocabulary Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anelia Angelova, Dahun Kim, Weicheng Kuo","submitted_at":"2023-09-29T21:56:37Z","abstract_excerpt":"We present a new open-vocabulary detection approach based on region-centric image-language pretraining to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we incorporate the detector architecture on top of the classification backbone, which better serves the region-level recognition needs of detection by enabling the detector heads to learn from large-scale image-text pairs. Using only standard contrastive loss and no pseudo-labeling, our approach is a simple yet effective extension of the contrastive learning method to learn emerge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00161","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/2310.00161/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":"2310.00161","created_at":"2026-07-05T08:45:46.732326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00161v2","created_at":"2026-07-05T08:45:46.732326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00161","created_at":"2026-07-05T08:45:46.732326+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYL5LWMRRK3J","created_at":"2026-07-05T08:45:46.732326+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYL5LWMRRK3JDLOU","created_at":"2026-07-05T08:45:46.732326+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYL5LWMR","created_at":"2026-07-05T08:45:46.732326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28271","citing_title":"LV-OSD: Language-Vision-Complementary Open-Set Object Detection","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y","json":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y.json","graph_json":"https://pith.science/api/pith-number/XYL5LWMRRK3JDLOUGE5MA4QX2Y/graph.json","events_json":"https://pith.science/api/pith-number/XYL5LWMRRK3JDLOUGE5MA4QX2Y/events.json","paper":"https://pith.science/paper/XYL5LWMR"},"agent_actions":{"view_html":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y","download_json":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y.json","view_paper":"https://pith.science/paper/XYL5LWMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00161&json=true","fetch_graph":"https://pith.science/api/pith-number/XYL5LWMRRK3JDLOUGE5MA4QX2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/XYL5LWMRRK3JDLOUGE5MA4QX2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y/action/storage_attestation","attest_author":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y/action/author_attestation","sign_citation":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y/action/citation_signature","submit_replication":"https://pith.science/pith/XYL5LWMRRK3JDLOUGE5MA4QX2Y/action/replication_record"}},"created_at":"2026-07-05T08:45:46.732326+00:00","updated_at":"2026-07-05T08:45:46.732326+00:00"}