{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SGCLOXTZRAR3N5QA4F5KN4NDIU","short_pith_number":"pith:SGCLOXTZ","schema_version":"1.0","canonical_sha256":"9184b75e798823b6f600e17aa6f1a3452a815ebcef559d27b0af925d49329a32","source":{"kind":"arxiv","id":"2005.13616","version":1},"attestation_state":"computed","paper":{"title":"Modality Dropout for Improved Performance-driven Talking Faces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Nicholas Apostoloff, Paul Dixon, Reinhard Knothe, Sachin Kajareker","submitted_at":"2020-05-27T19:55:33Z","abstract_excerpt":"We describe our novel deep learning approach for driving animated faces using both acoustic and visual information. In particular, speech-related facial movements are generated using audiovisual information, and non-speech facial movements are generated using only visual information. To ensure that our model exploits both modalities during training, batches are generated that contain audio-only, video-only, and audiovisual input features. The probability of dropping a modality allows control over the degree to which the model exploits audio and visual information during training. Our trained m"},"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":"2005.13616","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-27T19:55:33Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"5658e51512b33443cc6c9a8d58474f22b9011a6f4096bfa0490e419b77c1fba9","abstract_canon_sha256":"5fafe9b4b29250b9569ae81e01fae3566b66eebedb1a6f5a155b1c8f61e9d5fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:23.637776Z","signature_b64":"SzRBgNphi+xMsYGv1n858z4uan/dQ+Z2eo45lXVf2p+Qwpwwa/j00rO9bZts5LeKs8hdXUyjW3G36DlRJP5sCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9184b75e798823b6f600e17aa6f1a3452a815ebcef559d27b0af925d49329a32","last_reissued_at":"2026-07-05T01:06:23.637393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:23.637393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modality Dropout for Improved Performance-driven Talking Faces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Nicholas Apostoloff, Paul Dixon, Reinhard Knothe, Sachin Kajareker","submitted_at":"2020-05-27T19:55:33Z","abstract_excerpt":"We describe our novel deep learning approach for driving animated faces using both acoustic and visual information. In particular, speech-related facial movements are generated using audiovisual information, and non-speech facial movements are generated using only visual information. To ensure that our model exploits both modalities during training, batches are generated that contain audio-only, video-only, and audiovisual input features. The probability of dropping a modality allows control over the degree to which the model exploits audio and visual information during training. Our trained m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13616","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/2005.13616/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":"2005.13616","created_at":"2026-07-05T01:06:23.637450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.13616v1","created_at":"2026-07-05T01:06:23.637450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13616","created_at":"2026-07-05T01:06:23.637450+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGCLOXTZRAR3","created_at":"2026-07-05T01:06:23.637450+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGCLOXTZRAR3N5QA","created_at":"2026-07-05T01:06:23.637450+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGCLOXTZ","created_at":"2026-07-05T01:06:23.637450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00865","citing_title":"Negative to Positive Co-learning with Aggressive Modality Dropout","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU","json":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU.json","graph_json":"https://pith.science/api/pith-number/SGCLOXTZRAR3N5QA4F5KN4NDIU/graph.json","events_json":"https://pith.science/api/pith-number/SGCLOXTZRAR3N5QA4F5KN4NDIU/events.json","paper":"https://pith.science/paper/SGCLOXTZ"},"agent_actions":{"view_html":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU","download_json":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU.json","view_paper":"https://pith.science/paper/SGCLOXTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.13616&json=true","fetch_graph":"https://pith.science/api/pith-number/SGCLOXTZRAR3N5QA4F5KN4NDIU/graph.json","fetch_events":"https://pith.science/api/pith-number/SGCLOXTZRAR3N5QA4F5KN4NDIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU/action/storage_attestation","attest_author":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU/action/author_attestation","sign_citation":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU/action/citation_signature","submit_replication":"https://pith.science/pith/SGCLOXTZRAR3N5QA4F5KN4NDIU/action/replication_record"}},"created_at":"2026-07-05T01:06:23.637450+00:00","updated_at":"2026-07-05T01:06:23.637450+00:00"}