{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TJFCOFSJO2D62M4BEFPPECV3TN","short_pith_number":"pith:TJFCOFSJ","schema_version":"1.0","canonical_sha256":"9a4a2716497687ed3381215ef20abb9b7489e4ba4650f17be4df8404e0d48232","source":{"kind":"arxiv","id":"2303.14386","version":1},"attestation_state":"computed","paper":{"title":"Prompt-Guided Transformers for End-to-End Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hwanjun Song, Jihwan Bang","submitted_at":"2023-03-25T07:31:08Z","abstract_excerpt":"Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classes. Additionally, our novel RoI-based masked attention and RoI pruning techniques help leverage the zero-shot classification ability of the Vision Transformer-based CLIP, resulting in improved detection performance at minimal computational cost. Our experiments on the OV-COCO and OVLVIS datasets demonstrate that Prompt-OVD achieves an impressive 21.2 times faster inference speed"},"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":"2303.14386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-25T07:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"e095f19caf60ec833840775778cf4e0a723302d34eaa613d0fd8bc1209ab1980","abstract_canon_sha256":"ba078ed82a2afdce072b51bec92642da035785e1b3faaaecd0cec36418cc1a63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:40.818922Z","signature_b64":"vku4NGn1Na+OBBlqu3PLhkBkOHX2yb+LXvXfa+E+AuuhTHTtXtZc6KmZ14pSyZHrawABhSelCPklRzwMnERvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a4a2716497687ed3381215ef20abb9b7489e4ba4650f17be4df8404e0d48232","last_reissued_at":"2026-07-05T05:54:40.818508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:40.818508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-Guided Transformers for End-to-End Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hwanjun Song, Jihwan Bang","submitted_at":"2023-03-25T07:31:08Z","abstract_excerpt":"Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classes. Additionally, our novel RoI-based masked attention and RoI pruning techniques help leverage the zero-shot classification ability of the Vision Transformer-based CLIP, resulting in improved detection performance at minimal computational cost. Our experiments on the OV-COCO and OVLVIS datasets demonstrate that Prompt-OVD achieves an impressive 21.2 times faster inference speed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14386","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/2303.14386/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":"2303.14386","created_at":"2026-07-05T05:54:40.818564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14386v1","created_at":"2026-07-05T05:54:40.818564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14386","created_at":"2026-07-05T05:54:40.818564+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJFCOFSJO2D6","created_at":"2026-07-05T05:54:40.818564+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJFCOFSJO2D62M4B","created_at":"2026-07-05T05:54:40.818564+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJFCOFSJ","created_at":"2026-07-05T05:54:40.818564+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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN","json":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN.json","graph_json":"https://pith.science/api/pith-number/TJFCOFSJO2D62M4BEFPPECV3TN/graph.json","events_json":"https://pith.science/api/pith-number/TJFCOFSJO2D62M4BEFPPECV3TN/events.json","paper":"https://pith.science/paper/TJFCOFSJ"},"agent_actions":{"view_html":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN","download_json":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN.json","view_paper":"https://pith.science/paper/TJFCOFSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14386&json=true","fetch_graph":"https://pith.science/api/pith-number/TJFCOFSJO2D62M4BEFPPECV3TN/graph.json","fetch_events":"https://pith.science/api/pith-number/TJFCOFSJO2D62M4BEFPPECV3TN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN/action/storage_attestation","attest_author":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN/action/author_attestation","sign_citation":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN/action/citation_signature","submit_replication":"https://pith.science/pith/TJFCOFSJO2D62M4BEFPPECV3TN/action/replication_record"}},"created_at":"2026-07-05T05:54:40.818564+00:00","updated_at":"2026-07-05T05:54:40.818564+00:00"}