{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LKQIPUVS6TADE5RDNC3JAEA2YW","short_pith_number":"pith:LKQIPUVS","schema_version":"1.0","canonical_sha256":"5aa087d2b2f4c032762368b690101ac58d3fef9c98f8b1889d06bcf3bf16a766","source":{"kind":"arxiv","id":"2501.13452","version":2},"attestation_state":"computed","paper":{"title":"EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyuan Liu, Jiangchuan Wei, Mingyu Guo, Renjie Chen, Shiyue Yan, Wenfeng Lin","submitted_at":"2025-01-23T08:06:11Z","abstract_excerpt":"Recent advancements in video generation have significantly impacted various downstream applications, particularly in identity-preserving video generation (IPT2V). However, existing methods struggle with \"copy-paste\" artifacts and low similarity issues, primarily due to their reliance on low-level facial image information. This dependence can result in rigid facial appearances and artifacts reflecting irrelevant details. To address these challenges, we propose EchoVideo, which employs two key strategies: (1) an Identity Image-Text Fusion Module (IITF) that integrates high-level semantic feature"},"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":"2501.13452","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T08:06:11Z","cross_cats_sorted":[],"title_canon_sha256":"d83c15dceeedb9c0b8b3562181a4092d02e3c2580ca76064cc7f5f24e85f2b1f","abstract_canon_sha256":"4bb424ccecd4573fcea5328a0d6e0c510f72df6dff8aa1a45770cdc402979585"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:43.074325Z","signature_b64":"elnIYgZzuSjWVKxJa74hHHdwCGxUx2sBYcenugltHPCM7/z7HnB4Q30ukiqx3x24PRqeD42hal5A3cBRLE4YDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aa087d2b2f4c032762368b690101ac58d3fef9c98f8b1889d06bcf3bf16a766","last_reissued_at":"2026-07-05T10:20:43.073597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:43.073597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyuan Liu, Jiangchuan Wei, Mingyu Guo, Renjie Chen, Shiyue Yan, Wenfeng Lin","submitted_at":"2025-01-23T08:06:11Z","abstract_excerpt":"Recent advancements in video generation have significantly impacted various downstream applications, particularly in identity-preserving video generation (IPT2V). However, existing methods struggle with \"copy-paste\" artifacts and low similarity issues, primarily due to their reliance on low-level facial image information. This dependence can result in rigid facial appearances and artifacts reflecting irrelevant details. To address these challenges, we propose EchoVideo, which employs two key strategies: (1) an Identity Image-Text Fusion Module (IITF) that integrates high-level semantic feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13452","kind":"arxiv","version":2},"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/2501.13452/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":"2501.13452","created_at":"2026-07-05T10:20:43.073690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13452v2","created_at":"2026-07-05T10:20:43.073690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13452","created_at":"2026-07-05T10:20:43.073690+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKQIPUVS6TAD","created_at":"2026-07-05T10:20:43.073690+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKQIPUVS6TADE5RD","created_at":"2026-07-05T10:20:43.073690+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKQIPUVS","created_at":"2026-07-05T10:20:43.073690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11670","citing_title":"ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02441","citing_title":"Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW","json":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW.json","graph_json":"https://pith.science/api/pith-number/LKQIPUVS6TADE5RDNC3JAEA2YW/graph.json","events_json":"https://pith.science/api/pith-number/LKQIPUVS6TADE5RDNC3JAEA2YW/events.json","paper":"https://pith.science/paper/LKQIPUVS"},"agent_actions":{"view_html":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW","download_json":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW.json","view_paper":"https://pith.science/paper/LKQIPUVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13452&json=true","fetch_graph":"https://pith.science/api/pith-number/LKQIPUVS6TADE5RDNC3JAEA2YW/graph.json","fetch_events":"https://pith.science/api/pith-number/LKQIPUVS6TADE5RDNC3JAEA2YW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW/action/storage_attestation","attest_author":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW/action/author_attestation","sign_citation":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW/action/citation_signature","submit_replication":"https://pith.science/pith/LKQIPUVS6TADE5RDNC3JAEA2YW/action/replication_record"}},"created_at":"2026-07-05T10:20:43.073690+00:00","updated_at":"2026-07-05T10:20:43.073690+00:00"}