{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LU2QXEEYIJBZQGCELNVQ727JEO","short_pith_number":"pith:LU2QXEEY","schema_version":"1.0","canonical_sha256":"5d350b909842439818445b6b0febe923b53b036a0890b720d96c59fe4d992483","source":{"kind":"arxiv","id":"2209.05946","version":2},"attestation_state":"computed","paper":{"title":"OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Kyusong Lee, Peng Liu, Tiancheng Zhao","submitted_at":"2022-09-10T14:25:14Z","abstract_excerpt":"The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an innovative training mechanism that harnesses continual learning and multi-dataset vision-language pre-training. Leveraging natural language as a universal knowledge representation, OmDet accumulates a \"visual vocabulary\" from diverse datasets, unifying the task as a language-conditioned detection framework. Our multimodal detection network (MDN) overcomes the challenges of multi-"},"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":"2209.05946","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-10T14:25:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a94724a2510423dc4ed8a0f81477239a265743df0d089510d09b02d29f922e3b","abstract_canon_sha256":"95905343ec763b19ae5de69979da21478bccb6cd8efaf1bf89b58423c1dce163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:43.787304Z","signature_b64":"wUwxiXXkP1YTnHN6lPNAZ1ERPTRDAVU5/GG+MA3Nm1cD3X+gNmr+89ZgFR1MBvqf3+zyymUATlJ0gcbH5w6zDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d350b909842439818445b6b0febe923b53b036a0890b720d96c59fe4d992483","last_reissued_at":"2026-07-05T07:48:43.786890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:43.786890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Kyusong Lee, Peng Liu, Tiancheng Zhao","submitted_at":"2022-09-10T14:25:14Z","abstract_excerpt":"The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an innovative training mechanism that harnesses continual learning and multi-dataset vision-language pre-training. Leveraging natural language as a universal knowledge representation, OmDet accumulates a \"visual vocabulary\" from diverse datasets, unifying the task as a language-conditioned detection framework. Our multimodal detection network (MDN) overcomes the challenges of multi-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05946","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/2209.05946/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":"2209.05946","created_at":"2026-07-05T07:48:43.786947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.05946v2","created_at":"2026-07-05T07:48:43.786947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05946","created_at":"2026-07-05T07:48:43.786947+00:00"},{"alias_kind":"pith_short_12","alias_value":"LU2QXEEYIJBZ","created_at":"2026-07-05T07:48:43.786947+00:00"},{"alias_kind":"pith_short_16","alias_value":"LU2QXEEYIJBZQGCE","created_at":"2026-07-05T07:48:43.786947+00:00"},{"alias_kind":"pith_short_8","alias_value":"LU2QXEEY","created_at":"2026-07-05T07:48:43.786947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09799","citing_title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO","json":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO.json","graph_json":"https://pith.science/api/pith-number/LU2QXEEYIJBZQGCELNVQ727JEO/graph.json","events_json":"https://pith.science/api/pith-number/LU2QXEEYIJBZQGCELNVQ727JEO/events.json","paper":"https://pith.science/paper/LU2QXEEY"},"agent_actions":{"view_html":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO","download_json":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO.json","view_paper":"https://pith.science/paper/LU2QXEEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.05946&json=true","fetch_graph":"https://pith.science/api/pith-number/LU2QXEEYIJBZQGCELNVQ727JEO/graph.json","fetch_events":"https://pith.science/api/pith-number/LU2QXEEYIJBZQGCELNVQ727JEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO/action/storage_attestation","attest_author":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO/action/author_attestation","sign_citation":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO/action/citation_signature","submit_replication":"https://pith.science/pith/LU2QXEEYIJBZQGCELNVQ727JEO/action/replication_record"}},"created_at":"2026-07-05T07:48:43.786947+00:00","updated_at":"2026-07-05T07:48:43.786947+00:00"}