{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UOK2R2DXFZ3XJXARXUQBHE5VWZ","short_pith_number":"pith:UOK2R2DX","schema_version":"1.0","canonical_sha256":"a395a8e8772e7774dc11bd201393b5b6632e7ebc062590b210ade5b375360801","source":{"kind":"arxiv","id":"2204.03795","version":2},"attestation_state":"computed","paper":{"title":"Semantic Representation and Dependency Learning for Multi-Label Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hefeng Wu, Liang Lin, Ling Tian, Mingzhan Sun, Tao Pu, Tianshui Chen","submitted_at":"2022-04-08T00:55:15Z","abstract_excerpt":"Recently many multi-label image recognition (MLR) works have made significant progress by introducing pre-trained object detection models to generate lots of proposals or utilizing statistical label co-occurrence enhance the correlation among different categories. However, these works have some limitations: (1) the effectiveness of the network significantly depends on pre-trained object detection models that bring expensive and unaffordable computation; (2) the network performance degrades when there exist occasional co-occurrence objects in images, especially for the rare categories. To addre"},"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":"2204.03795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-08T00:55:15Z","cross_cats_sorted":[],"title_canon_sha256":"f1badf217b4e3b83cca12a7af4dc6c967248ce36efcd38261bfa599cc5767877","abstract_canon_sha256":"0d06da8b0e872e85dc0db384d18037a663f6126f01f5b3b0b02b7d330681d1c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:14.030208Z","signature_b64":"0RDRvDUttck8ZZtYFUuPEtSGEV/gDN6zT5SesT7NWmkhOeQmQEK8sdqik/ABEDpSH67E1Yh/XY2z6SMvvma6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a395a8e8772e7774dc11bd201393b5b6632e7ebc062590b210ade5b375360801","last_reissued_at":"2026-07-05T05:31:14.029667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:14.029667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Representation and Dependency Learning for Multi-Label Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hefeng Wu, Liang Lin, Ling Tian, Mingzhan Sun, Tao Pu, Tianshui Chen","submitted_at":"2022-04-08T00:55:15Z","abstract_excerpt":"Recently many multi-label image recognition (MLR) works have made significant progress by introducing pre-trained object detection models to generate lots of proposals or utilizing statistical label co-occurrence enhance the correlation among different categories. However, these works have some limitations: (1) the effectiveness of the network significantly depends on pre-trained object detection models that bring expensive and unaffordable computation; (2) the network performance degrades when there exist occasional co-occurrence objects in images, especially for the rare categories. To addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03795","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/2204.03795/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":"2204.03795","created_at":"2026-07-05T05:31:14.029726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03795v2","created_at":"2026-07-05T05:31:14.029726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03795","created_at":"2026-07-05T05:31:14.029726+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOK2R2DXFZ3X","created_at":"2026-07-05T05:31:14.029726+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOK2R2DXFZ3XJXAR","created_at":"2026-07-05T05:31:14.029726+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOK2R2DX","created_at":"2026-07-05T05:31:14.029726+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/UOK2R2DXFZ3XJXARXUQBHE5VWZ","json":"https://pith.science/pith/UOK2R2DXFZ3XJXARXUQBHE5VWZ.json","graph_json":"https://pith.science/api/pith-number/UOK2R2DXFZ3XJXARXUQBHE5VWZ/graph.json","events_json":"https://pith.science/api/pith-number/UOK2R2DXFZ3XJXARXUQBHE5VWZ/events.json","paper":"https://pith.science/paper/UOK2R2DX"},"agent_actions":{"view_html":"https://pith.science/pith/UOK2R2DXFZ3XJXARXUQBHE5VWZ","download_json":"https://pith.science/pith/UOK2R2DXFZ3XJXARXUQBHE5VWZ.json","view_paper":"https://pith.science/paper/UOK2R2DX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03795&json=true","fetch_graph":"https://pith.science/api/pith-number/UOK2R2DXFZ3XJXARXUQBHE5VWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UOK2R2DXFZ3XJXARXUQBHE5VWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOK2R2DXFZ3XJXARXUQBHE5VWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOK2R2DXFZ3XJXARXUQBHE5VWZ/action/storage_attestation","attest_author":"https://pith.science/pith/UOK2R2DXFZ3XJXARXUQBHE5VWZ/action/author_attestation","sign_citation":"https://pith.science/pith/UOK2R2DXFZ3XJXARXUQBHE5VWZ/action/citation_signature","submit_replication":"https://pith.science/pith/UOK2R2DXFZ3XJXARXUQBHE5VWZ/action/replication_record"}},"created_at":"2026-07-05T05:31:14.029726+00:00","updated_at":"2026-07-05T05:31:14.029726+00:00"}