{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BLLD7HTDEBQ3U4VCJJGQ5PK2LV","short_pith_number":"pith:BLLD7HTD","schema_version":"1.0","canonical_sha256":"0ad63f9e632061ba72a24a4d0ebd5a5d543bcaffeefdda47b1889f0c3b52e7c5","source":{"kind":"arxiv","id":"2407.07844","version":2},"attestation_state":"computed","paper":{"title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjian Feng, Dongmei Jiang, Hao Wang, Lin Ma, Pengzhen Ren, Xiangyuan Lan, Xiaodan Liang, Xiao Dong, Yaowei Wang, Yinlong Qian, Zequn Jie","submitted_at":"2024-07-10T17:05:49Z","abstract_excerpt":"Open-vocabulary detection is a challenging task due to the requirement of detecting objects based on class names, including those not encountered during training. Existing methods have shown strong zero-shot detection capabilities through pre-training and pseudo-labeling on diverse large-scale datasets. However, these approaches encounter two main challenges: (i) how to effectively eliminate data noise from pseudo-labeling, and (ii) how to efficiently leverage the language-aware capability for region-level cross-modality fusion and alignment. To address these challenges, we propose a novel uni"},"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":"2407.07844","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T17:05:49Z","cross_cats_sorted":[],"title_canon_sha256":"834163626d29acc253d75e17e6e92f70d2af257edd966273d99016b0d5fb2934","abstract_canon_sha256":"af8dd8f37eb27aacadac731275128cdd6bd70a0999dcf677625ce3b4e53906ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:27.193077Z","signature_b64":"bpSKjYfasahVChyXK8UQoZsoUxyTQjeVmXTU2JelKFmgLEGEVnZEFca3AcB0gBe1XKvJC0B2fPPK89385uXRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ad63f9e632061ba72a24a4d0ebd5a5d543bcaffeefdda47b1889f0c3b52e7c5","last_reissued_at":"2026-07-05T08:46:27.192589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:27.192589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjian Feng, Dongmei Jiang, Hao Wang, Lin Ma, Pengzhen Ren, Xiangyuan Lan, Xiaodan Liang, Xiao Dong, Yaowei Wang, Yinlong Qian, Zequn Jie","submitted_at":"2024-07-10T17:05:49Z","abstract_excerpt":"Open-vocabulary detection is a challenging task due to the requirement of detecting objects based on class names, including those not encountered during training. Existing methods have shown strong zero-shot detection capabilities through pre-training and pseudo-labeling on diverse large-scale datasets. However, these approaches encounter two main challenges: (i) how to effectively eliminate data noise from pseudo-labeling, and (ii) how to efficiently leverage the language-aware capability for region-level cross-modality fusion and alignment. To address these challenges, we propose a novel uni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07844","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/2407.07844/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":"2407.07844","created_at":"2026-07-05T08:46:27.192649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07844v2","created_at":"2026-07-05T08:46:27.192649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07844","created_at":"2026-07-05T08:46:27.192649+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLLD7HTDEBQ3","created_at":"2026-07-05T08:46:27.192649+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLLD7HTDEBQ3U4VC","created_at":"2026-07-05T08:46:27.192649+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLLD7HTD","created_at":"2026-07-05T08:46:27.192649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08014","citing_title":"Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV","json":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV.json","graph_json":"https://pith.science/api/pith-number/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/graph.json","events_json":"https://pith.science/api/pith-number/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/events.json","paper":"https://pith.science/paper/BLLD7HTD"},"agent_actions":{"view_html":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV","download_json":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV.json","view_paper":"https://pith.science/paper/BLLD7HTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07844&json=true","fetch_graph":"https://pith.science/api/pith-number/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/graph.json","fetch_events":"https://pith.science/api/pith-number/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/action/storage_attestation","attest_author":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/action/author_attestation","sign_citation":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/action/citation_signature","submit_replication":"https://pith.science/pith/BLLD7HTDEBQ3U4VCJJGQ5PK2LV/action/replication_record"}},"created_at":"2026-07-05T08:46:27.192649+00:00","updated_at":"2026-07-05T08:46:27.192649+00:00"}