{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JGKJPGXD4QCSKZW3H5RK3BCH4E","short_pith_number":"pith:JGKJPGXD","schema_version":"1.0","canonical_sha256":"4994979ae3e4052566db3f62ad8447e12e1cff0b7f917df376c463858c33364d","source":{"kind":"arxiv","id":"2209.09407","version":2},"attestation_state":"computed","paper":{"title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunjing Xu, Dan Xu, Hang Xu, Jianhua Han, Lewei Yao, Wei Zhang, Xiaodan Liang, Youpeng Wen, Zhenguo Li","submitted_at":"2022-09-20T02:01:01Z","abstract_excerpt":"Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all category names of detection datasets into sentences, which leads to inefficient interaction between category names. This paper presents DetCLIP, a paralleled visual-concept pre-training method for open-world detection by resorting to knowledge enrichment from a designed concept dictionary. To achieve better learning efficiency, we propose a novel paralleled conc"},"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":"2209.09407","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-20T02:01:01Z","cross_cats_sorted":[],"title_canon_sha256":"18bb2db9ff10dcc047ed0abcffafe26a9be7658ecba620d38c3452dddd7a0f84","abstract_canon_sha256":"89a71ac4dd23ba632d7034afc52be8a57f0291b3dc27da9be36e9719c1fb4761"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:03.229527Z","signature_b64":"V7F41O1ZGfuOSzrr4N8Y7hqDnKS3wuJWJupIWSGpcFgQorXfvHdYzEeO7AEnXQt4qOPnxihoCaKgJgQ1OxSyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4994979ae3e4052566db3f62ad8447e12e1cff0b7f917df376c463858c33364d","last_reissued_at":"2026-07-05T05:07:03.229057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:03.229057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunjing Xu, Dan Xu, Hang Xu, Jianhua Han, Lewei Yao, Wei Zhang, Xiaodan Liang, Youpeng Wen, Zhenguo Li","submitted_at":"2022-09-20T02:01:01Z","abstract_excerpt":"Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all category names of detection datasets into sentences, which leads to inefficient interaction between category names. This paper presents DetCLIP, a paralleled visual-concept pre-training method for open-world detection by resorting to knowledge enrichment from a designed concept dictionary. To achieve better learning efficiency, we propose a novel paralleled conc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09407","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/2209.09407/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":"2209.09407","created_at":"2026-07-05T05:07:03.229115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.09407v2","created_at":"2026-07-05T05:07:03.229115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09407","created_at":"2026-07-05T05:07:03.229115+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGKJPGXD4QCS","created_at":"2026-07-05T05:07:03.229115+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGKJPGXD4QCSKZW3","created_at":"2026-07-05T05:07:03.229115+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGKJPGXD","created_at":"2026-07-05T05:07:03.229115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18594","citing_title":"EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E","json":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E.json","graph_json":"https://pith.science/api/pith-number/JGKJPGXD4QCSKZW3H5RK3BCH4E/graph.json","events_json":"https://pith.science/api/pith-number/JGKJPGXD4QCSKZW3H5RK3BCH4E/events.json","paper":"https://pith.science/paper/JGKJPGXD"},"agent_actions":{"view_html":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E","download_json":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E.json","view_paper":"https://pith.science/paper/JGKJPGXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.09407&json=true","fetch_graph":"https://pith.science/api/pith-number/JGKJPGXD4QCSKZW3H5RK3BCH4E/graph.json","fetch_events":"https://pith.science/api/pith-number/JGKJPGXD4QCSKZW3H5RK3BCH4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E/action/storage_attestation","attest_author":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E/action/author_attestation","sign_citation":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E/action/citation_signature","submit_replication":"https://pith.science/pith/JGKJPGXD4QCSKZW3H5RK3BCH4E/action/replication_record"}},"created_at":"2026-07-05T05:07:03.229115+00:00","updated_at":"2026-07-05T05:07:03.229115+00:00"}