{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6CKVGCITT5BDEKVXVIXT5LTZCR","short_pith_number":"pith:6CKVGCIT","schema_version":"1.0","canonical_sha256":"f0955309139f42322ab7aa2f3eae79145219305f3df98bf3667d0c6387a8de6f","source":{"kind":"arxiv","id":"2406.01188","version":1},"attestation_state":"computed","paper":{"title":"UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Jiayu Wang, Luxin Yan, Nong Sang, Shiwei Zhang, Xiang Wang, Xiaoqiang Zhou, Yingya Zhang","submitted_at":"2024-06-03T10:51:10Z","abstract_excerpt":"Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still two limitations: i) an extra reference model is required to align the identity image with the main video branch, which significantly increases the optimization burden and model parameters; ii) the generated video is usually short in time (e.g., 24 frames), hampering practical applications. To address these shortcomings, we present a UniAnimate framework to ena"},"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":"2406.01188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T10:51:10Z","cross_cats_sorted":[],"title_canon_sha256":"12157b3de80ba35e3c9e17595c83be758b2eada67a487232363c72a7b1d24431","abstract_canon_sha256":"0eaf3999ca3827ae3863e9ced9cdd06b323b909002bd791f49e9740e09150fd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:36.613552Z","signature_b64":"eQdSe0S6glmUcXUjlbdKdxGGdJp+EhbrmdZ0z5/YbXlGWA5IlNWRgVzHt/ZA4oQhQgGFtNnPlGkn/P6c7W26CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0955309139f42322ab7aa2f3eae79145219305f3df98bf3667d0c6387a8de6f","last_reissued_at":"2026-07-05T08:26:36.613066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:36.613066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Jiayu Wang, Luxin Yan, Nong Sang, Shiwei Zhang, Xiang Wang, Xiaoqiang Zhou, Yingya Zhang","submitted_at":"2024-06-03T10:51:10Z","abstract_excerpt":"Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still two limitations: i) an extra reference model is required to align the identity image with the main video branch, which significantly increases the optimization burden and model parameters; ii) the generated video is usually short in time (e.g., 24 frames), hampering practical applications. To address these shortcomings, we present a UniAnimate framework to ena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01188","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/2406.01188/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":"2406.01188","created_at":"2026-07-05T08:26:36.613121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01188v1","created_at":"2026-07-05T08:26:36.613121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01188","created_at":"2026-07-05T08:26:36.613121+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CKVGCITT5BD","created_at":"2026-07-05T08:26:36.613121+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CKVGCITT5BDEKVX","created_at":"2026-07-05T08:26:36.613121+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CKVGCIT","created_at":"2026-07-05T08:26:36.613121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.22940","citing_title":"One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21431","citing_title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2501.03575","citing_title":"Cosmos World Foundation Model Platform for Physical AI","ref_index":209,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR","json":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR.json","graph_json":"https://pith.science/api/pith-number/6CKVGCITT5BDEKVXVIXT5LTZCR/graph.json","events_json":"https://pith.science/api/pith-number/6CKVGCITT5BDEKVXVIXT5LTZCR/events.json","paper":"https://pith.science/paper/6CKVGCIT"},"agent_actions":{"view_html":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR","download_json":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR.json","view_paper":"https://pith.science/paper/6CKVGCIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01188&json=true","fetch_graph":"https://pith.science/api/pith-number/6CKVGCITT5BDEKVXVIXT5LTZCR/graph.json","fetch_events":"https://pith.science/api/pith-number/6CKVGCITT5BDEKVXVIXT5LTZCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR/action/storage_attestation","attest_author":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR/action/author_attestation","sign_citation":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR/action/citation_signature","submit_replication":"https://pith.science/pith/6CKVGCITT5BDEKVXVIXT5LTZCR/action/replication_record"}},"created_at":"2026-07-05T08:26:36.613121+00:00","updated_at":"2026-07-05T08:26:36.613121+00:00"}