{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CEHJDTZV2I7YBDWNS3NOOPDJ7K","short_pith_number":"pith:CEHJDTZV","schema_version":"1.0","canonical_sha256":"110e91cf35d23f808ecd96dae73c69fa84279a2a6e1ebdc5797e452727728920","source":{"kind":"arxiv","id":"2204.08451","version":1},"attestation_state":"computed","paper":{"title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angjoo Kanazawa, Evonne Ng, Hanbyul Joo, Hao Li, Liwen Hu, Shiry Ginosar, Trevor Darrell","submitted_at":"2022-04-18T17:58:04Z","abstract_excerpt":"We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of corresponding listener motion. We combine the motion and speech audio of the speaker using a motion-audio cross attention transformer. Furthermore, we enable non-deterministic prediction by learning a discrete latent representation of realistic listener motion with a novel motion-encoding VQ-VAE. Our method organically captures the multimodal and non-deterministic nature of nonverbal dyadic interactions. Moreover, it"},"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":"2204.08451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T17:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"9c95414e59422105b2ef9f1788d2e4e1b13692827547a6bf6837c8bad9624d67","abstract_canon_sha256":"f9c11ac1aaeccf8821eff5f62635f71947ba29494ffb9f72f898edc48f81c6cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:26.231518Z","signature_b64":"gMHN6q9lpt62ePNhkaVOFtMW/uOv1fTFEqUgd0hzDDtVKLyihs9WsP5Lq2Dyy29NIsSCDJ3df3H1MzmvjG3wBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"110e91cf35d23f808ecd96dae73c69fa84279a2a6e1ebdc5797e452727728920","last_reissued_at":"2026-07-05T04:15:26.231018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:26.231018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angjoo Kanazawa, Evonne Ng, Hanbyul Joo, Hao Li, Liwen Hu, Shiry Ginosar, Trevor Darrell","submitted_at":"2022-04-18T17:58:04Z","abstract_excerpt":"We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of corresponding listener motion. We combine the motion and speech audio of the speaker using a motion-audio cross attention transformer. Furthermore, we enable non-deterministic prediction by learning a discrete latent representation of realistic listener motion with a novel motion-encoding VQ-VAE. Our method organically captures the multimodal and non-deterministic nature of nonverbal dyadic interactions. Moreover, it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08451","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/2204.08451/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":"2204.08451","created_at":"2026-07-05T04:15:26.231077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08451v1","created_at":"2026-07-05T04:15:26.231077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08451","created_at":"2026-07-05T04:15:26.231077+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEHJDTZV2I7Y","created_at":"2026-07-05T04:15:26.231077+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEHJDTZV2I7YBDWN","created_at":"2026-07-05T04:15:26.231077+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEHJDTZV","created_at":"2026-07-05T04:15:26.231077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05896","citing_title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K","json":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K.json","graph_json":"https://pith.science/api/pith-number/CEHJDTZV2I7YBDWNS3NOOPDJ7K/graph.json","events_json":"https://pith.science/api/pith-number/CEHJDTZV2I7YBDWNS3NOOPDJ7K/events.json","paper":"https://pith.science/paper/CEHJDTZV"},"agent_actions":{"view_html":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K","download_json":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K.json","view_paper":"https://pith.science/paper/CEHJDTZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08451&json=true","fetch_graph":"https://pith.science/api/pith-number/CEHJDTZV2I7YBDWNS3NOOPDJ7K/graph.json","fetch_events":"https://pith.science/api/pith-number/CEHJDTZV2I7YBDWNS3NOOPDJ7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K/action/storage_attestation","attest_author":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K/action/author_attestation","sign_citation":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K/action/citation_signature","submit_replication":"https://pith.science/pith/CEHJDTZV2I7YBDWNS3NOOPDJ7K/action/replication_record"}},"created_at":"2026-07-05T04:15:26.231077+00:00","updated_at":"2026-07-05T04:15:26.231077+00:00"}