{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PXT2QBRNO4ZB6BNHZVAWH5EUVT","short_pith_number":"pith:PXT2QBRN","schema_version":"1.0","canonical_sha256":"7de7a8062d77321f05a7cd4163f494ace530452191367a9c0a5ff3111a25edff","source":{"kind":"arxiv","id":"2002.07227","version":1},"attestation_state":"computed","paper":{"title":"Dual-Attention GAN for Large-Pose Face Frontalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joseph P. Robinson, Songyao Jiang, Yun Fu, Yu Yin","submitted_at":"2020-02-17T20:00:56Z","abstract_excerpt":"Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario. Despite recent advances in deep learning-based face synthesis approaches, this problem is still challenging due to significant pose and illumination discrepancy. In this paper, we present a novel Dual-Attention Generative Adversarial Network (DA-GAN) for photo-realistic face frontalization by capturing both contextual dependencies and local consistency during GAN training. Specifically, a self-attention-based generator is introdu"},"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":"2002.07227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-17T20:00:56Z","cross_cats_sorted":[],"title_canon_sha256":"3b86d373a577461f38db664d48488e37813cfefb123bbd5d458a1b2385b83d58","abstract_canon_sha256":"e66db48e51694463ac307228784d42dd704d71fa06d255bfe5e21d386bfafb4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:14.617027Z","signature_b64":"PyLTihZMXh+51B/EVMT6DRY8/4ekp8QlgoZT1i/AyQXyW9XHK23EqTzqhcbJ62qzds1Zg0Srn74xd6fl/vaMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7de7a8062d77321f05a7cd4163f494ace530452191367a9c0a5ff3111a25edff","last_reissued_at":"2026-07-05T00:41:14.616602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:14.616602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-Attention GAN for Large-Pose Face Frontalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joseph P. Robinson, Songyao Jiang, Yun Fu, Yu Yin","submitted_at":"2020-02-17T20:00:56Z","abstract_excerpt":"Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario. Despite recent advances in deep learning-based face synthesis approaches, this problem is still challenging due to significant pose and illumination discrepancy. In this paper, we present a novel Dual-Attention Generative Adversarial Network (DA-GAN) for photo-realistic face frontalization by capturing both contextual dependencies and local consistency during GAN training. Specifically, a self-attention-based generator is introdu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07227","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/2002.07227/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":"2002.07227","created_at":"2026-07-05T00:41:14.616670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07227v1","created_at":"2026-07-05T00:41:14.616670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07227","created_at":"2026-07-05T00:41:14.616670+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXT2QBRNO4ZB","created_at":"2026-07-05T00:41:14.616670+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXT2QBRNO4ZB6BNH","created_at":"2026-07-05T00:41:14.616670+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXT2QBRN","created_at":"2026-07-05T00:41:14.616670+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/PXT2QBRNO4ZB6BNHZVAWH5EUVT","json":"https://pith.science/pith/PXT2QBRNO4ZB6BNHZVAWH5EUVT.json","graph_json":"https://pith.science/api/pith-number/PXT2QBRNO4ZB6BNHZVAWH5EUVT/graph.json","events_json":"https://pith.science/api/pith-number/PXT2QBRNO4ZB6BNHZVAWH5EUVT/events.json","paper":"https://pith.science/paper/PXT2QBRN"},"agent_actions":{"view_html":"https://pith.science/pith/PXT2QBRNO4ZB6BNHZVAWH5EUVT","download_json":"https://pith.science/pith/PXT2QBRNO4ZB6BNHZVAWH5EUVT.json","view_paper":"https://pith.science/paper/PXT2QBRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07227&json=true","fetch_graph":"https://pith.science/api/pith-number/PXT2QBRNO4ZB6BNHZVAWH5EUVT/graph.json","fetch_events":"https://pith.science/api/pith-number/PXT2QBRNO4ZB6BNHZVAWH5EUVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXT2QBRNO4ZB6BNHZVAWH5EUVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXT2QBRNO4ZB6BNHZVAWH5EUVT/action/storage_attestation","attest_author":"https://pith.science/pith/PXT2QBRNO4ZB6BNHZVAWH5EUVT/action/author_attestation","sign_citation":"https://pith.science/pith/PXT2QBRNO4ZB6BNHZVAWH5EUVT/action/citation_signature","submit_replication":"https://pith.science/pith/PXT2QBRNO4ZB6BNHZVAWH5EUVT/action/replication_record"}},"created_at":"2026-07-05T00:41:14.616670+00:00","updated_at":"2026-07-05T00:41:14.616670+00:00"}