{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JSFL5CX2IN2PUPGSGQTIZP3BXJ","short_pith_number":"pith:JSFL5CX2","schema_version":"1.0","canonical_sha256":"4c8abe8afa4374fa3cd234268cbf61ba5a3014befca75a109cf7734ec1a16adb","source":{"kind":"arxiv","id":"2004.12452","version":1},"attestation_state":"computed","paper":{"title":"One-Shot Identity-Preserving Portrait Reenactment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwei Chen, Hao Li, Koki Nagano, Mingming He, Pengda Xiang, Sitao Xiang, Yuming Gu","submitted_at":"2020-04-26T18:30:33Z","abstract_excerpt":"We present a deep learning-based framework for portrait reenactment from a single picture of a target (one-shot) and a video of a driving subject. Existing facial reenactment methods suffer from identity mismatch and produce inconsistent identities when a target and a driving subject are different (cross-subject), especially in one-shot settings. In this work, we aim to address identity preservation in cross-subject portrait reenactment from a single picture. We introduce a novel technique that can disentangle identity from expressions and poses, allowing identity preserving portrait reenactme"},"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":"2004.12452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-26T18:30:33Z","cross_cats_sorted":[],"title_canon_sha256":"4fc4af8e41092f0df857ed790d74669c56a4aaa3625f868d6adcafff69a70eb3","abstract_canon_sha256":"1e579b0510a1c9fe7a81457f9bfeb87d29677041bbba9dd723ae90f2b3dab3ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:15.661251Z","signature_b64":"JK2Jayepte18IjgFKKG/yyjZHHNx7xsSTMEBbwn5UjM18E+HOcLbVSWPplorv57KIDxfPkng9iiV3lkUiIk7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c8abe8afa4374fa3cd234268cbf61ba5a3014befca75a109cf7734ec1a16adb","last_reissued_at":"2026-07-05T00:58:15.660739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:15.660739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Shot Identity-Preserving Portrait Reenactment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwei Chen, Hao Li, Koki Nagano, Mingming He, Pengda Xiang, Sitao Xiang, Yuming Gu","submitted_at":"2020-04-26T18:30:33Z","abstract_excerpt":"We present a deep learning-based framework for portrait reenactment from a single picture of a target (one-shot) and a video of a driving subject. Existing facial reenactment methods suffer from identity mismatch and produce inconsistent identities when a target and a driving subject are different (cross-subject), especially in one-shot settings. In this work, we aim to address identity preservation in cross-subject portrait reenactment from a single picture. We introduce a novel technique that can disentangle identity from expressions and poses, allowing identity preserving portrait reenactme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12452","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/2004.12452/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":"2004.12452","created_at":"2026-07-05T00:58:15.660816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.12452v1","created_at":"2026-07-05T00:58:15.660816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12452","created_at":"2026-07-05T00:58:15.660816+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSFL5CX2IN2P","created_at":"2026-07-05T00:58:15.660816+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSFL5CX2IN2PUPGS","created_at":"2026-07-05T00:58:15.660816+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSFL5CX2","created_at":"2026-07-05T00:58:15.660816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10369","citing_title":"Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ","json":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ.json","graph_json":"https://pith.science/api/pith-number/JSFL5CX2IN2PUPGSGQTIZP3BXJ/graph.json","events_json":"https://pith.science/api/pith-number/JSFL5CX2IN2PUPGSGQTIZP3BXJ/events.json","paper":"https://pith.science/paper/JSFL5CX2"},"agent_actions":{"view_html":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ","download_json":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ.json","view_paper":"https://pith.science/paper/JSFL5CX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.12452&json=true","fetch_graph":"https://pith.science/api/pith-number/JSFL5CX2IN2PUPGSGQTIZP3BXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JSFL5CX2IN2PUPGSGQTIZP3BXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ/action/storage_attestation","attest_author":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ/action/author_attestation","sign_citation":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ/action/citation_signature","submit_replication":"https://pith.science/pith/JSFL5CX2IN2PUPGSGQTIZP3BXJ/action/replication_record"}},"created_at":"2026-07-05T00:58:15.660816+00:00","updated_at":"2026-07-05T00:58:15.660816+00:00"}