{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PRH3LIQUNQ2CDR7VDOKNJWIJ2V","short_pith_number":"pith:PRH3LIQU","schema_version":"1.0","canonical_sha256":"7c4fb5a2146c3421c7f51b94d4d909d55e299146a5e099215e9bfcf21c04e32b","source":{"kind":"arxiv","id":"2501.18954","version":1},"attestation_state":"computed","paper":{"title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingke Meng, Junkai Yan, Qijie Mo, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Xihan Wei","submitted_at":"2025-01-31T08:27:31Z","abstract_excerpt":"Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption gener"},"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":"2501.18954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T08:27:31Z","cross_cats_sorted":[],"title_canon_sha256":"b3bca5e15f8428b9b0eff18e2d7a378b5826cc2a186e3e7c371a7eacfa4137b2","abstract_canon_sha256":"365c777b83f30301c5da6834d99b6c9e44dde218384d06ab13a3d1da385026a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:54.039198Z","signature_b64":"UjPLaHA3Q9TheeNFQ+CW38TcKaMWhSJXtizjYCRJzT8SqxTou1DWS54ccTBvTw5dmKUccQg4oqU5of4grhHKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c4fb5a2146c3421c7f51b94d4d909d55e299146a5e099215e9bfcf21c04e32b","last_reissued_at":"2026-07-05T10:07:54.038721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:54.038721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingke Meng, Junkai Yan, Qijie Mo, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Xihan Wei","submitted_at":"2025-01-31T08:27:31Z","abstract_excerpt":"Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18954","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/2501.18954/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":"2501.18954","created_at":"2026-07-05T10:07:54.038779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18954v1","created_at":"2026-07-05T10:07:54.038779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18954","created_at":"2026-07-05T10:07:54.038779+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRH3LIQUNQ2C","created_at":"2026-07-05T10:07:54.038779+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRH3LIQUNQ2CDR7V","created_at":"2026-07-05T10:07:54.038779+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRH3LIQU","created_at":"2026-07-05T10:07:54.038779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03784","citing_title":"Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V","json":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V.json","graph_json":"https://pith.science/api/pith-number/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/graph.json","events_json":"https://pith.science/api/pith-number/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/events.json","paper":"https://pith.science/paper/PRH3LIQU"},"agent_actions":{"view_html":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V","download_json":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V.json","view_paper":"https://pith.science/paper/PRH3LIQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18954&json=true","fetch_graph":"https://pith.science/api/pith-number/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/graph.json","fetch_events":"https://pith.science/api/pith-number/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/action/storage_attestation","attest_author":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/action/author_attestation","sign_citation":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/action/citation_signature","submit_replication":"https://pith.science/pith/PRH3LIQUNQ2CDR7VDOKNJWIJ2V/action/replication_record"}},"created_at":"2026-07-05T10:07:54.038779+00:00","updated_at":"2026-07-05T10:07:54.038779+00:00"}