{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GLCNYBV5ROLIPJFHQXFDTPWEVO","short_pith_number":"pith:GLCNYBV5","schema_version":"1.0","canonical_sha256":"32c4dc06bd8b9687a4a785ca39bec4ab86529faf08236eb984ffc86550ccf99d","source":{"kind":"arxiv","id":"1603.08907","version":1},"attestation_state":"computed","paper":{"title":"Cross-modal Supervision for Learning Active Speaker Detection in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Punarjay Chakravarty, Tinne Tuytelaars","submitted_at":"2016-03-29T19:47:46Z","abstract_excerpt":"In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based classifier in a weakly supervised manner. The classifier uses spatio-temporal features to encode upper body motion - facial expressions and gesticulations associated with speaking. We further improve a generic model for active speaker detection by learning person specific models. Finally, we demonstrate the online adaptation of generic models learnt on one dataset, to previously unseen people in a new dataset, again using"},"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":"1603.08907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-29T19:47:46Z","cross_cats_sorted":[],"title_canon_sha256":"c9d6e6f25fb47122cd3b9a1a0aa36daab390d237729235fb158f39f8932b3f1b","abstract_canon_sha256":"2d652f762584773fa5faba0ce466c0056f7cc722b7795165956dc882f4410f4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:04.996967Z","signature_b64":"DkMjNXd9ywh8XAh6MWsCGEGzBi6ENGb97+XVIrbkuI4lDoh+aZQVyGSsuGg9mR/huushCxpWAZKmlrMXNVzUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32c4dc06bd8b9687a4a785ca39bec4ab86529faf08236eb984ffc86550ccf99d","last_reissued_at":"2026-05-18T01:18:04.996171Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:04.996171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-modal Supervision for Learning Active Speaker Detection in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Punarjay Chakravarty, Tinne Tuytelaars","submitted_at":"2016-03-29T19:47:46Z","abstract_excerpt":"In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based classifier in a weakly supervised manner. The classifier uses spatio-temporal features to encode upper body motion - facial expressions and gesticulations associated with speaking. We further improve a generic model for active speaker detection by learning person specific models. Finally, we demonstrate the online adaptation of generic models learnt on one dataset, to previously unseen people in a new dataset, again using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08907","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":"1603.08907","created_at":"2026-05-18T01:18:04.996291+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.08907v1","created_at":"2026-05-18T01:18:04.996291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08907","created_at":"2026-05-18T01:18:04.996291+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLCNYBV5ROLI","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLCNYBV5ROLIPJFH","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLCNYBV5","created_at":"2026-05-18T12:30:19.053100+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/GLCNYBV5ROLIPJFHQXFDTPWEVO","json":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO.json","graph_json":"https://pith.science/api/pith-number/GLCNYBV5ROLIPJFHQXFDTPWEVO/graph.json","events_json":"https://pith.science/api/pith-number/GLCNYBV5ROLIPJFHQXFDTPWEVO/events.json","paper":"https://pith.science/paper/GLCNYBV5"},"agent_actions":{"view_html":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO","download_json":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO.json","view_paper":"https://pith.science/paper/GLCNYBV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.08907&json=true","fetch_graph":"https://pith.science/api/pith-number/GLCNYBV5ROLIPJFHQXFDTPWEVO/graph.json","fetch_events":"https://pith.science/api/pith-number/GLCNYBV5ROLIPJFHQXFDTPWEVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/action/storage_attestation","attest_author":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/action/author_attestation","sign_citation":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/action/citation_signature","submit_replication":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/action/replication_record"}},"created_at":"2026-05-18T01:18:04.996291+00:00","updated_at":"2026-05-18T01:18:04.996291+00:00"}