{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UY2U6RQ5FBNPC2AWO72Q25NTPG","short_pith_number":"pith:UY2U6RQ5","schema_version":"1.0","canonical_sha256":"a6354f461d285af1681677f50d75b3799c2803a28211fb7c9ae3e6c36e0b6283","source":{"kind":"arxiv","id":"2501.10687","version":1},"attestation_state":"computed","paper":{"title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Liefeng Bo, Linrui Tian, Qi Wang, Siqi Hu","submitted_at":"2025-01-18T07:51:29Z","abstract_excerpt":"In this paper, we propose a novel audio-driven talking head method capable of simultaneously generating highly expressive facial expressions and hand gestures. Unlike existing methods that focus on generating full-body or half-body poses, we investigate the challenges of co-speech gesture generation and identify the weak correspondence between audio features and full-body gestures as a key limitation. To address this, we redefine the task as a two-stage process. In the first stage, we generate hand poses directly from audio input, leveraging the strong correlation between audio signals and han"},"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":"2501.10687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T07:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"25db5ad499b95b81cc5750cb1557ba71824545c1374350396bd482204dfaf2cf","abstract_canon_sha256":"f7cb2173119adea2a690c7d4059121c8f6f8621893e167b42dbd02ed74d9d93c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:31.920994Z","signature_b64":"kaYlPPW8dl7XUONWVAQ2gNkGTvBd/GvwP4yPd6xbOFnS30Mzz8gZrQJXoBCquq7Mrev+4PQSjmGmJhyFU7LPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6354f461d285af1681677f50d75b3799c2803a28211fb7c9ae3e6c36e0b6283","last_reissued_at":"2026-07-05T10:02:31.920459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:31.920459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Liefeng Bo, Linrui Tian, Qi Wang, Siqi Hu","submitted_at":"2025-01-18T07:51:29Z","abstract_excerpt":"In this paper, we propose a novel audio-driven talking head method capable of simultaneously generating highly expressive facial expressions and hand gestures. Unlike existing methods that focus on generating full-body or half-body poses, we investigate the challenges of co-speech gesture generation and identify the weak correspondence between audio features and full-body gestures as a key limitation. To address this, we redefine the task as a two-stage process. In the first stage, we generate hand poses directly from audio input, leveraging the strong correlation between audio signals and han"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10687","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/2501.10687/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":"2501.10687","created_at":"2026-07-05T10:02:31.920525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10687v1","created_at":"2026-07-05T10:02:31.920525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10687","created_at":"2026-07-05T10:02:31.920525+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY2U6RQ5FBNP","created_at":"2026-07-05T10:02:31.920525+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY2U6RQ5FBNPC2AW","created_at":"2026-07-05T10:02:31.920525+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY2U6RQ5","created_at":"2026-07-05T10:02:31.920525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18467","citing_title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG","json":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG.json","graph_json":"https://pith.science/api/pith-number/UY2U6RQ5FBNPC2AWO72Q25NTPG/graph.json","events_json":"https://pith.science/api/pith-number/UY2U6RQ5FBNPC2AWO72Q25NTPG/events.json","paper":"https://pith.science/paper/UY2U6RQ5"},"agent_actions":{"view_html":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG","download_json":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG.json","view_paper":"https://pith.science/paper/UY2U6RQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10687&json=true","fetch_graph":"https://pith.science/api/pith-number/UY2U6RQ5FBNPC2AWO72Q25NTPG/graph.json","fetch_events":"https://pith.science/api/pith-number/UY2U6RQ5FBNPC2AWO72Q25NTPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/action/storage_attestation","attest_author":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/action/author_attestation","sign_citation":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/action/citation_signature","submit_replication":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/action/replication_record"}},"created_at":"2026-07-05T10:02:31.920525+00:00","updated_at":"2026-07-05T10:02:31.920525+00:00"}