{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WAMDGQNGQ34OEXDXV423QYDWZL","short_pith_number":"pith:WAMDGQNG","schema_version":"1.0","canonical_sha256":"b0183341a686f8e25c77af35b86076cafe88bbc133cadfcb014fc3175f8606b9","source":{"kind":"arxiv","id":"2405.19854","version":1},"attestation_state":"computed","paper":{"title":"RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyi Chen, Han Zhang, Hao Chen, Kai Hu, Marios Savvides, Zhantao Yang","submitted_at":"2024-05-30T09:03:23Z","abstract_excerpt":"Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs. However, such data is limited in practice due to significant annotation costs. In this work, we propose RTGen to generate scalable open-vocabulary region-text pairs and demonstrate its capability to boost the performance of open-vocabulary object detection. RTGen includes both text-to-region and region-to-text generation processes on scalable image-caption data. The text-to-region generation is powered by image inpainting, directed by our pr"},"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":"2405.19854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T09:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"d6d12c747216073f67539966a1d0a90892ce44b8e7ee819dfd8a817a62258806","abstract_canon_sha256":"ae9aa1ca6407126a6b9dc83b6f635d62130951a14acf7fa3933f067f67e9f163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:13.376334Z","signature_b64":"GzA9IyEnvaRkZNYwC2qUL4+lm/jdYbVRx2Z+xk48KMiPPnTuze7gk5/QburdstP4WPHJkcYrZURfO0Vuf9ZRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0183341a686f8e25c77af35b86076cafe88bbc133cadfcb014fc3175f8606b9","last_reissued_at":"2026-07-05T08:25:13.375974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:13.375974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyi Chen, Han Zhang, Hao Chen, Kai Hu, Marios Savvides, Zhantao Yang","submitted_at":"2024-05-30T09:03:23Z","abstract_excerpt":"Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs. However, such data is limited in practice due to significant annotation costs. In this work, we propose RTGen to generate scalable open-vocabulary region-text pairs and demonstrate its capability to boost the performance of open-vocabulary object detection. RTGen includes both text-to-region and region-to-text generation processes on scalable image-caption data. The text-to-region generation is powered by image inpainting, directed by our pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19854","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/2405.19854/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":"2405.19854","created_at":"2026-07-05T08:25:13.376032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19854v1","created_at":"2026-07-05T08:25:13.376032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19854","created_at":"2026-07-05T08:25:13.376032+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAMDGQNGQ34O","created_at":"2026-07-05T08:25:13.376032+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAMDGQNGQ34OEXDX","created_at":"2026-07-05T08:25:13.376032+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAMDGQNG","created_at":"2026-07-05T08:25:13.376032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00684","citing_title":"Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL","json":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL.json","graph_json":"https://pith.science/api/pith-number/WAMDGQNGQ34OEXDXV423QYDWZL/graph.json","events_json":"https://pith.science/api/pith-number/WAMDGQNGQ34OEXDXV423QYDWZL/events.json","paper":"https://pith.science/paper/WAMDGQNG"},"agent_actions":{"view_html":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL","download_json":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL.json","view_paper":"https://pith.science/paper/WAMDGQNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19854&json=true","fetch_graph":"https://pith.science/api/pith-number/WAMDGQNGQ34OEXDXV423QYDWZL/graph.json","fetch_events":"https://pith.science/api/pith-number/WAMDGQNGQ34OEXDXV423QYDWZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/action/storage_attestation","attest_author":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/action/author_attestation","sign_citation":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/action/citation_signature","submit_replication":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/action/replication_record"}},"created_at":"2026-07-05T08:25:13.376032+00:00","updated_at":"2026-07-05T08:25:13.376032+00:00"}