{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I5J45MXKKHM324A4GKVYZCFKYN","short_pith_number":"pith:I5J45MXK","schema_version":"1.0","canonical_sha256":"4753ceb2ea51d9bd701c32ab8c88aac3604c9bfa6631fe34151eab405a247856","source":{"kind":"arxiv","id":"2409.15179","version":1},"attestation_state":"computed","paper":{"title":"MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junwei Zhu, Keke He, Xiangtai Li, Xiaozhong Ji, Yong Liu, Yue Han, Yuxiang Feng, Zhucun Xue","submitted_at":"2024-09-23T16:33:53Z","abstract_excerpt":"Current diffusion-based face animation methods generally adopt a ReferenceNet (a copy of U-Net) and a large amount of curated self-acquired data to learn appearance features, as robust appearance features are vital for ensuring temporal stability. However, when trained on public datasets, the results often exhibit a noticeable performance gap in image quality and temporal consistency. To address this issue, we meticulously examine the essential appearance features in the facial animation tasks, which include motion-agnostic (e.g., clothing, background) and motion-related (e.g., facial details)"},"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":"2409.15179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T16:33:53Z","cross_cats_sorted":[],"title_canon_sha256":"3c3defbaf66fcf77736478bef7cdc5ab6d5ca51d6e5658faeca624b0075181a1","abstract_canon_sha256":"bc2388374f1b820ee27aa66b70332bb2890ca1d10ce41036378b6f15056d2fb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:37.327379Z","signature_b64":"HQfdFumGMJYwVvXsGXVrTXM118QGdJ75d5vk8nn7PSkr5Y+yQ2Htez51HMpEfv5BdyXEhAC4TERAM6pBw1CZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4753ceb2ea51d9bd701c32ab8c88aac3604c9bfa6631fe34151eab405a247856","last_reissued_at":"2026-07-05T09:10:37.326867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:37.326867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junwei Zhu, Keke He, Xiangtai Li, Xiaozhong Ji, Yong Liu, Yue Han, Yuxiang Feng, Zhucun Xue","submitted_at":"2024-09-23T16:33:53Z","abstract_excerpt":"Current diffusion-based face animation methods generally adopt a ReferenceNet (a copy of U-Net) and a large amount of curated self-acquired data to learn appearance features, as robust appearance features are vital for ensuring temporal stability. However, when trained on public datasets, the results often exhibit a noticeable performance gap in image quality and temporal consistency. To address this issue, we meticulously examine the essential appearance features in the facial animation tasks, which include motion-agnostic (e.g., clothing, background) and motion-related (e.g., facial details)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15179","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/2409.15179/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":"2409.15179","created_at":"2026-07-05T09:10:37.326927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15179v1","created_at":"2026-07-05T09:10:37.326927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15179","created_at":"2026-07-05T09:10:37.326927+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5J45MXKKHM3","created_at":"2026-07-05T09:10:37.326927+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5J45MXKKHM324A4","created_at":"2026-07-05T09:10:37.326927+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5J45MXK","created_at":"2026-07-05T09:10:37.326927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.13442","citing_title":"EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN","json":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN.json","graph_json":"https://pith.science/api/pith-number/I5J45MXKKHM324A4GKVYZCFKYN/graph.json","events_json":"https://pith.science/api/pith-number/I5J45MXKKHM324A4GKVYZCFKYN/events.json","paper":"https://pith.science/paper/I5J45MXK"},"agent_actions":{"view_html":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN","download_json":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN.json","view_paper":"https://pith.science/paper/I5J45MXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15179&json=true","fetch_graph":"https://pith.science/api/pith-number/I5J45MXKKHM324A4GKVYZCFKYN/graph.json","fetch_events":"https://pith.science/api/pith-number/I5J45MXKKHM324A4GKVYZCFKYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN/action/storage_attestation","attest_author":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN/action/author_attestation","sign_citation":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN/action/citation_signature","submit_replication":"https://pith.science/pith/I5J45MXKKHM324A4GKVYZCFKYN/action/replication_record"}},"created_at":"2026-07-05T09:10:37.326927+00:00","updated_at":"2026-07-05T09:10:37.326927+00:00"}