{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2RP6KSPSZ2Z2HJNPNZ7ITNSBOP","short_pith_number":"pith:2RP6KSPS","schema_version":"1.0","canonical_sha256":"d45fe549f2ceb3a3a5af6e7e89b64173e7bcabf7738e0bec40a4a4c47edee62b","source":{"kind":"arxiv","id":"1905.03820","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Lele Chen, Ross K. Maddox, Zhiyao Duan","submitted_at":"2019-05-09T19:14:26Z","abstract_excerpt":"We devise a cascade GAN approach to generate talking face video, which is robust to different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead of learning a direct mapping from audio to video frames, we propose first to transfer audio to high-level structure, i.e., the facial landmarks, and then to generate video frames conditioned on the landmarks. Compared to a direct audio-to-image approach, our cascade approach avoids fitting spurious correlations between audiovisual signals that are irrelevant to the speech content. We, humans, are sensitive to tempora"},"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":"1905.03820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-09T19:14:26Z","cross_cats_sorted":[],"title_canon_sha256":"23169dbe48b905012d59c9a3761512110fb7f7c530c30ef317dbed6123b54f21","abstract_canon_sha256":"40fbe5e48d6a14dfe1b61427e9b305df68855718cf8cad945b68aaf2760a9c4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:35.531344Z","signature_b64":"FKrkSRXw7BHX5TorGjmgYmVlZC66zg2Q0KHyENPbdyZTrXiwk2rLcU6gOYuh9KyuhGpcIQd+h3JQGlsMeyC8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d45fe549f2ceb3a3a5af6e7e89b64173e7bcabf7738e0bec40a4a4c47edee62b","last_reissued_at":"2026-05-17T23:46:35.530799Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:35.530799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Lele Chen, Ross K. Maddox, Zhiyao Duan","submitted_at":"2019-05-09T19:14:26Z","abstract_excerpt":"We devise a cascade GAN approach to generate talking face video, which is robust to different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead of learning a direct mapping from audio to video frames, we propose first to transfer audio to high-level structure, i.e., the facial landmarks, and then to generate video frames conditioned on the landmarks. Compared to a direct audio-to-image approach, our cascade approach avoids fitting spurious correlations between audiovisual signals that are irrelevant to the speech content. We, humans, are sensitive to tempora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03820","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":""},"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":"1905.03820","created_at":"2026-05-17T23:46:35.530868+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.03820v1","created_at":"2026-05-17T23:46:35.530868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03820","created_at":"2026-05-17T23:46:35.530868+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RP6KSPSZ2Z2","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RP6KSPSZ2Z2HJNP","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RP6KSPS","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP","json":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP.json","graph_json":"https://pith.science/api/pith-number/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/graph.json","events_json":"https://pith.science/api/pith-number/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/events.json","paper":"https://pith.science/paper/2RP6KSPS"},"agent_actions":{"view_html":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP","download_json":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP.json","view_paper":"https://pith.science/paper/2RP6KSPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.03820&json=true","fetch_graph":"https://pith.science/api/pith-number/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/graph.json","fetch_events":"https://pith.science/api/pith-number/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/action/storage_attestation","attest_author":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/action/author_attestation","sign_citation":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/action/citation_signature","submit_replication":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/action/replication_record"}},"created_at":"2026-05-17T23:46:35.530868+00:00","updated_at":"2026-05-17T23:46:35.530868+00:00"}