{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7RLKJOOIJLZ3264GK2BYJQRJHG","short_pith_number":"pith:7RLKJOOI","schema_version":"1.0","canonical_sha256":"fc56a4b9c84af3bd7b86568384c229398ac250da4efed88e94a12f4974eb7863","source":{"kind":"arxiv","id":"2606.11546","version":1},"attestation_state":"computed","paper":{"title":"VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Linqi Song, Qinran Lin, Yong Li","submitted_at":"2026-06-10T01:13:49Z","abstract_excerpt":"Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In this paper, we propose VL-DINO, an open-vocabulary detector that enhances DINO through more effective exploitation of CLIP's vision-language knowledge. Specifically, a Query-guided Positive Sample Construction (QPSC) module is first developed to construct additional high-quality positive samples, enabling the vanilla DINO framework to better accommodate mixed training across he"},"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":"2606.11546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T01:13:49Z","cross_cats_sorted":[],"title_canon_sha256":"05a465bf4e7f989435c80b608ccb3400502a8ee641d86f2d51c67544f8482b5e","abstract_canon_sha256":"3a8c251d4671df903f3ccc5b0bb531eccb54a07e0e2b0415c2a0adb3e085b695"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:55.409655Z","signature_b64":"15iS+ui4c04EaBiibiY142nlcAX0+/G/EBDHgTEviNAcEhhtCO0Tl8/cmsbe+k/ZyFdyBqs4uksOLuWP2IeaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc56a4b9c84af3bd7b86568384c229398ac250da4efed88e94a12f4974eb7863","last_reissued_at":"2026-06-11T01:09:55.408859Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:55.408859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Linqi Song, Qinran Lin, Yong Li","submitted_at":"2026-06-10T01:13:49Z","abstract_excerpt":"Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In this paper, we propose VL-DINO, an open-vocabulary detector that enhances DINO through more effective exploitation of CLIP's vision-language knowledge. Specifically, a Query-guided Positive Sample Construction (QPSC) module is first developed to construct additional high-quality positive samples, enabling the vanilla DINO framework to better accommodate mixed training across he"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11546","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/2606.11546/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":"2606.11546","created_at":"2026-06-11T01:09:55.408983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11546v1","created_at":"2026-06-11T01:09:55.408983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11546","created_at":"2026-06-11T01:09:55.408983+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RLKJOOIJLZ3","created_at":"2026-06-11T01:09:55.408983+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RLKJOOIJLZ3264G","created_at":"2026-06-11T01:09:55.408983+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RLKJOOI","created_at":"2026-06-11T01:09:55.408983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG","json":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG.json","graph_json":"https://pith.science/api/pith-number/7RLKJOOIJLZ3264GK2BYJQRJHG/graph.json","events_json":"https://pith.science/api/pith-number/7RLKJOOIJLZ3264GK2BYJQRJHG/events.json","paper":"https://pith.science/paper/7RLKJOOI"},"agent_actions":{"view_html":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG","download_json":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG.json","view_paper":"https://pith.science/paper/7RLKJOOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11546&json=true","fetch_graph":"https://pith.science/api/pith-number/7RLKJOOIJLZ3264GK2BYJQRJHG/graph.json","fetch_events":"https://pith.science/api/pith-number/7RLKJOOIJLZ3264GK2BYJQRJHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/action/storage_attestation","attest_author":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/action/author_attestation","sign_citation":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/action/citation_signature","submit_replication":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/action/replication_record"}},"created_at":"2026-06-11T01:09:55.408983+00:00","updated_at":"2026-06-11T01:09:55.408983+00:00"}