{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DHLMPU4MK6VHW2V4CJOYE6RGNG","short_pith_number":"pith:DHLMPU4M","schema_version":"1.0","canonical_sha256":"19d6c7d38c57aa7b6abc125d827a2669bd683fcbc68b57b33c452d5be0e95cb0","source":{"kind":"arxiv","id":"2308.15846","version":1},"attestation_state":"computed","paper":{"title":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Mengdan Zhang, Xiaoshan Yang, Yifan Xu","submitted_at":"2023-08-30T08:33:13Z","abstract_excerpt":"In this paper, we for the first time explore helpful multi-modal contextual knowledge to understand novel categories for open-vocabulary object detection (OVD). The multi-modal contextual knowledge stands for the joint relationship across regions and words. However, it is challenging to incorporate such multi-modal contextual knowledge into OVD. The reason is that previous detection frameworks fail to jointly model multi-modal contextual knowledge, as object detectors only support vision inputs and no caption description is provided at test time. To this end, we propose a multi-modal contextua"},"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":"2308.15846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T08:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"a3169dfcf970cc00e9bbeb74a0e00734f6960a72f66abc25ff73d2bf07e5cd02","abstract_canon_sha256":"bb1a21e27e70f03aaa594dade8b2d5c5384b5e2696c37f4872f95a7af0f1fbf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:14.134485Z","signature_b64":"7TeekQozzBQ8rANoglnFccjW2A/qJo8Ucl8FB1/z06TW3gBoh5PKs3MUWYNOl2fciEr9i8wAU06+P35d6FlUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d6c7d38c57aa7b6abc125d827a2669bd683fcbc68b57b33c452d5be0e95cb0","last_reissued_at":"2026-07-05T06:46:14.133986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:14.133986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Mengdan Zhang, Xiaoshan Yang, Yifan Xu","submitted_at":"2023-08-30T08:33:13Z","abstract_excerpt":"In this paper, we for the first time explore helpful multi-modal contextual knowledge to understand novel categories for open-vocabulary object detection (OVD). The multi-modal contextual knowledge stands for the joint relationship across regions and words. However, it is challenging to incorporate such multi-modal contextual knowledge into OVD. The reason is that previous detection frameworks fail to jointly model multi-modal contextual knowledge, as object detectors only support vision inputs and no caption description is provided at test time. To this end, we propose a multi-modal contextua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15846","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/2308.15846/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":"2308.15846","created_at":"2026-07-05T06:46:14.134049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15846v1","created_at":"2026-07-05T06:46:14.134049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15846","created_at":"2026-07-05T06:46:14.134049+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHLMPU4MK6VH","created_at":"2026-07-05T06:46:14.134049+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHLMPU4MK6VHW2V4","created_at":"2026-07-05T06:46:14.134049+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHLMPU4M","created_at":"2026-07-05T06:46:14.134049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09360","citing_title":"ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG","json":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG.json","graph_json":"https://pith.science/api/pith-number/DHLMPU4MK6VHW2V4CJOYE6RGNG/graph.json","events_json":"https://pith.science/api/pith-number/DHLMPU4MK6VHW2V4CJOYE6RGNG/events.json","paper":"https://pith.science/paper/DHLMPU4M"},"agent_actions":{"view_html":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG","download_json":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG.json","view_paper":"https://pith.science/paper/DHLMPU4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15846&json=true","fetch_graph":"https://pith.science/api/pith-number/DHLMPU4MK6VHW2V4CJOYE6RGNG/graph.json","fetch_events":"https://pith.science/api/pith-number/DHLMPU4MK6VHW2V4CJOYE6RGNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/action/storage_attestation","attest_author":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/action/author_attestation","sign_citation":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/action/citation_signature","submit_replication":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/action/replication_record"}},"created_at":"2026-07-05T06:46:14.134049+00:00","updated_at":"2026-07-05T06:46:14.134049+00:00"}