{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G3ABXARPHOAFJRFIREH36OVASI","short_pith_number":"pith:G3ABXARP","schema_version":"1.0","canonical_sha256":"36c01b822f3b8054c4a8890fbf3aa0921d1ed68abdf4dac40f60212ddfa9b262","source":{"kind":"arxiv","id":"2505.06663","version":1},"attestation_state":"computed","paper":{"title":"METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuo Yang, Xinxiao Wu, Yongqi Wang","submitted_at":"2025-05-10T14:45:43Z","abstract_excerpt":"Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of pre-trained vision-language models such as CLIP to identify novel categories. They typically adopt a cascaded pipeline to first detect objects and then classify relationships based on the detected objects, which may lead to error propagation and thus suboptimal performance. In this paper, we propose Mutual EnhancemenT of Objects and Relationships (METOR), a "},"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":"2505.06663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-10T14:45:43Z","cross_cats_sorted":[],"title_canon_sha256":"a2c638a14a94802094d367c199453e202ec40639efab81ff116e177971ae8307","abstract_canon_sha256":"35f52d4938b608adcabc71333d8ef46e3120538c33a5e526c077d98d0eecfb28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:13.882637Z","signature_b64":"mgAgX6VMgvspKvGC95pRLhuRyvSSmeuHikAO8lhu/l3biuLHA9A1Sqh4Fj5OISydy8UU2Zgjmn38fmxNvy/KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36c01b822f3b8054c4a8890fbf3aa0921d1ed68abdf4dac40f60212ddfa9b262","last_reissued_at":"2026-07-05T11:01:13.882071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:13.882071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuo Yang, Xinxiao Wu, Yongqi Wang","submitted_at":"2025-05-10T14:45:43Z","abstract_excerpt":"Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of pre-trained vision-language models such as CLIP to identify novel categories. They typically adopt a cascaded pipeline to first detect objects and then classify relationships based on the detected objects, which may lead to error propagation and thus suboptimal performance. In this paper, we propose Mutual EnhancemenT of Objects and Relationships (METOR), a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06663","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/2505.06663/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":"2505.06663","created_at":"2026-07-05T11:01:13.882135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06663v1","created_at":"2026-07-05T11:01:13.882135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06663","created_at":"2026-07-05T11:01:13.882135+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3ABXARPHOAF","created_at":"2026-07-05T11:01:13.882135+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3ABXARPHOAFJRFI","created_at":"2026-07-05T11:01:13.882135+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3ABXARP","created_at":"2026-07-05T11:01:13.882135+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/G3ABXARPHOAFJRFIREH36OVASI","json":"https://pith.science/pith/G3ABXARPHOAFJRFIREH36OVASI.json","graph_json":"https://pith.science/api/pith-number/G3ABXARPHOAFJRFIREH36OVASI/graph.json","events_json":"https://pith.science/api/pith-number/G3ABXARPHOAFJRFIREH36OVASI/events.json","paper":"https://pith.science/paper/G3ABXARP"},"agent_actions":{"view_html":"https://pith.science/pith/G3ABXARPHOAFJRFIREH36OVASI","download_json":"https://pith.science/pith/G3ABXARPHOAFJRFIREH36OVASI.json","view_paper":"https://pith.science/paper/G3ABXARP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06663&json=true","fetch_graph":"https://pith.science/api/pith-number/G3ABXARPHOAFJRFIREH36OVASI/graph.json","fetch_events":"https://pith.science/api/pith-number/G3ABXARPHOAFJRFIREH36OVASI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3ABXARPHOAFJRFIREH36OVASI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3ABXARPHOAFJRFIREH36OVASI/action/storage_attestation","attest_author":"https://pith.science/pith/G3ABXARPHOAFJRFIREH36OVASI/action/author_attestation","sign_citation":"https://pith.science/pith/G3ABXARPHOAFJRFIREH36OVASI/action/citation_signature","submit_replication":"https://pith.science/pith/G3ABXARPHOAFJRFIREH36OVASI/action/replication_record"}},"created_at":"2026-07-05T11:01:13.882135+00:00","updated_at":"2026-07-05T11:01:13.882135+00:00"}