{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YB6Z72IEYL2TBDNBDCZRV64MC6","short_pith_number":"pith:YB6Z72IE","schema_version":"1.0","canonical_sha256":"c07d9fe904c2f5308da118b31afb8c17bb7941b1ba1b40b0325d8be0cb559bb0","source":{"kind":"arxiv","id":"2107.02713","version":1},"attestation_state":"computed","paper":{"title":"Predicate correlation learning for scene graph generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leitian Tao, Li Mi, Nannan Li, Xianhang Cheng, Yaosi Hu, Zhenzhong Chen","submitted_at":"2021-07-06T16:24:33Z","abstract_excerpt":"For a typical Scene Graph Generation (SGG) method, there is often a large gap in the performance of the predicates' head classes and tail classes. This phenomenon is mainly caused by the semantic overlap between different predicates as well as the long-tailed data distribution. In this paper, a Predicate Correlation Learning (PCL) method for SGG is proposed to address the above two problems by taking the correlation between predicates into consideration. To describe the semantic overlap between strong-correlated predicate classes, a Predicate Correlation Matrix (PCM) is defined to quantify the"},"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":"2107.02713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-06T16:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"2425db14194d50d4b09e9ba650d93b24f8d37e2226edfcb511c1c7ca99e0ad91","abstract_canon_sha256":"ae8aa60537a0f9d7678cb71a251b74660998f0a3745667b41a9ddf3b86b38232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:18.854871Z","signature_b64":"6V0wvbE4yerDQN2VzDeLrgObszAcGo+Y3+XTpHK0zVa8pBSTwpp9N2Nk4NPL3onr1mR0mZAJzLI00DWNK4RjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c07d9fe904c2f5308da118b31afb8c17bb7941b1ba1b40b0325d8be0cb559bb0","last_reissued_at":"2026-07-05T04:39:18.854460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:18.854460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicate correlation learning for scene graph generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leitian Tao, Li Mi, Nannan Li, Xianhang Cheng, Yaosi Hu, Zhenzhong Chen","submitted_at":"2021-07-06T16:24:33Z","abstract_excerpt":"For a typical Scene Graph Generation (SGG) method, there is often a large gap in the performance of the predicates' head classes and tail classes. This phenomenon is mainly caused by the semantic overlap between different predicates as well as the long-tailed data distribution. In this paper, a Predicate Correlation Learning (PCL) method for SGG is proposed to address the above two problems by taking the correlation between predicates into consideration. To describe the semantic overlap between strong-correlated predicate classes, a Predicate Correlation Matrix (PCM) is defined to quantify the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02713","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/2107.02713/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":"2107.02713","created_at":"2026-07-05T04:39:18.854527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.02713v1","created_at":"2026-07-05T04:39:18.854527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02713","created_at":"2026-07-05T04:39:18.854527+00:00"},{"alias_kind":"pith_short_12","alias_value":"YB6Z72IEYL2T","created_at":"2026-07-05T04:39:18.854527+00:00"},{"alias_kind":"pith_short_16","alias_value":"YB6Z72IEYL2TBDNB","created_at":"2026-07-05T04:39:18.854527+00:00"},{"alias_kind":"pith_short_8","alias_value":"YB6Z72IE","created_at":"2026-07-05T04:39:18.854527+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/YB6Z72IEYL2TBDNBDCZRV64MC6","json":"https://pith.science/pith/YB6Z72IEYL2TBDNBDCZRV64MC6.json","graph_json":"https://pith.science/api/pith-number/YB6Z72IEYL2TBDNBDCZRV64MC6/graph.json","events_json":"https://pith.science/api/pith-number/YB6Z72IEYL2TBDNBDCZRV64MC6/events.json","paper":"https://pith.science/paper/YB6Z72IE"},"agent_actions":{"view_html":"https://pith.science/pith/YB6Z72IEYL2TBDNBDCZRV64MC6","download_json":"https://pith.science/pith/YB6Z72IEYL2TBDNBDCZRV64MC6.json","view_paper":"https://pith.science/paper/YB6Z72IE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.02713&json=true","fetch_graph":"https://pith.science/api/pith-number/YB6Z72IEYL2TBDNBDCZRV64MC6/graph.json","fetch_events":"https://pith.science/api/pith-number/YB6Z72IEYL2TBDNBDCZRV64MC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YB6Z72IEYL2TBDNBDCZRV64MC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YB6Z72IEYL2TBDNBDCZRV64MC6/action/storage_attestation","attest_author":"https://pith.science/pith/YB6Z72IEYL2TBDNBDCZRV64MC6/action/author_attestation","sign_citation":"https://pith.science/pith/YB6Z72IEYL2TBDNBDCZRV64MC6/action/citation_signature","submit_replication":"https://pith.science/pith/YB6Z72IEYL2TBDNBDCZRV64MC6/action/replication_record"}},"created_at":"2026-07-05T04:39:18.854527+00:00","updated_at":"2026-07-05T04:39:18.854527+00:00"}