{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2F6Z2RXUEAWVII473LBEG7CAK3","short_pith_number":"pith:2F6Z2RXU","schema_version":"1.0","canonical_sha256":"d17d9d46f4202d54239fdac2437c4056ece50b93b5eed04decba13276ad0a2ee","source":{"kind":"arxiv","id":"2105.13825","version":1},"attestation_state":"computed","paper":{"title":"Improving Facial Attribute Recognition by Group and Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhu, Jing Xu, Rui Zhao, Shuhang Gu, Zhenghao Chen","submitted_at":"2021-05-28T13:36:28Z","abstract_excerpt":"Exploiting the relationships between attributes is a key challenge for improving multiple facial attribute recognition. In this work, we are concerned with two types of correlations that are spatial and non-spatial relationships. For the spatial correlation, we aggregate attributes with spatial similarity into a part-based group and then introduce a Group Attention Learning to generate the group attention and the part-based group feature. On the other hand, to discover the non-spatial relationship, we model a group-based Graph Correlation Learning to explore affinities of predefined part-based"},"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":"2105.13825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-28T13:36:28Z","cross_cats_sorted":[],"title_canon_sha256":"9258399e4c2ee866400bc6e0f1b2110ae6e197aab39026ef33f2031f592a6cf7","abstract_canon_sha256":"1467241179d162fb8abbcedff1298c4d4846bd8a040d20c581bbf36b0b121e2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:11.913063Z","signature_b64":"cOiwbD4tdYwZg9B8N3QehkbX5sLEfSzWNHEssFDKozsupl0Jr7wajN2NDcllUv7+MgsjXnsrtpz7jpw3XiwrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17d9d46f4202d54239fdac2437c4056ece50b93b5eed04decba13276ad0a2ee","last_reissued_at":"2026-07-05T02:44:11.912561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:11.912561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Facial Attribute Recognition by Group and Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhu, Jing Xu, Rui Zhao, Shuhang Gu, Zhenghao Chen","submitted_at":"2021-05-28T13:36:28Z","abstract_excerpt":"Exploiting the relationships between attributes is a key challenge for improving multiple facial attribute recognition. In this work, we are concerned with two types of correlations that are spatial and non-spatial relationships. For the spatial correlation, we aggregate attributes with spatial similarity into a part-based group and then introduce a Group Attention Learning to generate the group attention and the part-based group feature. On the other hand, to discover the non-spatial relationship, we model a group-based Graph Correlation Learning to explore affinities of predefined part-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13825","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/2105.13825/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":"2105.13825","created_at":"2026-07-05T02:44:11.912623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13825v1","created_at":"2026-07-05T02:44:11.912623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13825","created_at":"2026-07-05T02:44:11.912623+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F6Z2RXUEAWV","created_at":"2026-07-05T02:44:11.912623+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F6Z2RXUEAWVII47","created_at":"2026-07-05T02:44:11.912623+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F6Z2RXU","created_at":"2026-07-05T02:44:11.912623+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/2F6Z2RXUEAWVII473LBEG7CAK3","json":"https://pith.science/pith/2F6Z2RXUEAWVII473LBEG7CAK3.json","graph_json":"https://pith.science/api/pith-number/2F6Z2RXUEAWVII473LBEG7CAK3/graph.json","events_json":"https://pith.science/api/pith-number/2F6Z2RXUEAWVII473LBEG7CAK3/events.json","paper":"https://pith.science/paper/2F6Z2RXU"},"agent_actions":{"view_html":"https://pith.science/pith/2F6Z2RXUEAWVII473LBEG7CAK3","download_json":"https://pith.science/pith/2F6Z2RXUEAWVII473LBEG7CAK3.json","view_paper":"https://pith.science/paper/2F6Z2RXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13825&json=true","fetch_graph":"https://pith.science/api/pith-number/2F6Z2RXUEAWVII473LBEG7CAK3/graph.json","fetch_events":"https://pith.science/api/pith-number/2F6Z2RXUEAWVII473LBEG7CAK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F6Z2RXUEAWVII473LBEG7CAK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F6Z2RXUEAWVII473LBEG7CAK3/action/storage_attestation","attest_author":"https://pith.science/pith/2F6Z2RXUEAWVII473LBEG7CAK3/action/author_attestation","sign_citation":"https://pith.science/pith/2F6Z2RXUEAWVII473LBEG7CAK3/action/citation_signature","submit_replication":"https://pith.science/pith/2F6Z2RXUEAWVII473LBEG7CAK3/action/replication_record"}},"created_at":"2026-07-05T02:44:11.912623+00:00","updated_at":"2026-07-05T02:44:11.912623+00:00"}