{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4QN3XPQAPXQWMW2ZJ4NUU447B7","short_pith_number":"pith:4QN3XPQA","schema_version":"1.0","canonical_sha256":"e41bbbbe007de1665b594f1b4a739f0fee794824521ca744933ab575eed75464","source":{"kind":"arxiv","id":"2011.15126","version":3},"attestation_state":"computed","paper":{"title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Mallya, Ming-Yu Liu, Ting-Chun Wang","submitted_at":"2020-11-30T18:56:35Z","abstract_excerpt":"We propose a neural talking-head video synthesis model and demonstrate its application to video conferencing. Our model learns to synthesize a talking-head video using a source image containing the target person's appearance and a driving video that dictates the motion in the output. Our motion is encoded based on a novel keypoint representation, where the identity-specific and motion-related information is decomposed unsupervisedly. Extensive experimental validation shows that our model outperforms competing methods on benchmark datasets. Moreover, our compact keypoint representation enables "},"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":"2011.15126","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-30T18:56:35Z","cross_cats_sorted":[],"title_canon_sha256":"3633c526a28441cb955330277298a0535aa4c62710b42c81e0326094a1f6a3b9","abstract_canon_sha256":"f6cf09e03e20a6480f6a0c2ff400c4659fafe2bc3cbcf5e06511238633bf51a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:53.965747Z","signature_b64":"K1IC16jQKVHDce3CF0ysH1tVLLdUIpVfiPSlEq04nusVh6LMF7rLs6ZeQHhZjqCXsRmnyV6pSSpj5ZyAm4LvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e41bbbbe007de1665b594f1b4a739f0fee794824521ca744933ab575eed75464","last_reissued_at":"2026-07-05T02:28:53.965192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:53.965192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Mallya, Ming-Yu Liu, Ting-Chun Wang","submitted_at":"2020-11-30T18:56:35Z","abstract_excerpt":"We propose a neural talking-head video synthesis model and demonstrate its application to video conferencing. Our model learns to synthesize a talking-head video using a source image containing the target person's appearance and a driving video that dictates the motion in the output. Our motion is encoded based on a novel keypoint representation, where the identity-specific and motion-related information is decomposed unsupervisedly. Extensive experimental validation shows that our model outperforms competing methods on benchmark datasets. Moreover, our compact keypoint representation enables "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.15126","kind":"arxiv","version":3},"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/2011.15126/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":"2011.15126","created_at":"2026-07-05T02:28:53.965262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.15126v3","created_at":"2026-07-05T02:28:53.965262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.15126","created_at":"2026-07-05T02:28:53.965262+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QN3XPQAPXQW","created_at":"2026-07-05T02:28:53.965262+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QN3XPQAPXQWMW2Z","created_at":"2026-07-05T02:28:53.965262+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QN3XPQA","created_at":"2026-07-05T02:28:53.965262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26223","citing_title":"StreamGuard: Exploring a 5G Architecture for Efficient, Quality of Experience-Aware Video Conferencing","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26223","citing_title":"StreamGuard: Exploring a 5G Architecture for Efficient, Quality of Experience-Aware Video Conferencing","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26223","citing_title":"StreamGuard: Exploring a 5G Architecture for Efficient, Quality of Experience-Aware Video Conferencing","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7","json":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7.json","graph_json":"https://pith.science/api/pith-number/4QN3XPQAPXQWMW2ZJ4NUU447B7/graph.json","events_json":"https://pith.science/api/pith-number/4QN3XPQAPXQWMW2ZJ4NUU447B7/events.json","paper":"https://pith.science/paper/4QN3XPQA"},"agent_actions":{"view_html":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7","download_json":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7.json","view_paper":"https://pith.science/paper/4QN3XPQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.15126&json=true","fetch_graph":"https://pith.science/api/pith-number/4QN3XPQAPXQWMW2ZJ4NUU447B7/graph.json","fetch_events":"https://pith.science/api/pith-number/4QN3XPQAPXQWMW2ZJ4NUU447B7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7/action/storage_attestation","attest_author":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7/action/author_attestation","sign_citation":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7/action/citation_signature","submit_replication":"https://pith.science/pith/4QN3XPQAPXQWMW2ZJ4NUU447B7/action/replication_record"}},"created_at":"2026-07-05T02:28:53.965262+00:00","updated_at":"2026-07-05T02:28:53.965262+00:00"}