{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:GLCNYBV5ROLIPJFHQXFDTPWEVO","short_pith_number":"pith:GLCNYBV5","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"},"canonical_sha256":"32c4dc06bd8b9687a4a785ca39bec4ab86529faf08236eb984ffc86550ccf99d","source":{"kind":"arxiv","id":"1603.08907","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.08907","created_at":"2026-05-18T01:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"1603.08907v1","created_at":"2026-05-18T01:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08907","created_at":"2026-05-18T01:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"GLCNYBV5ROLI","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GLCNYBV5ROLIPJFH","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GLCNYBV5","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:GLCNYBV5ROLIPJFHQXFDTPWEVO","target":"record","payload":{"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"},"canonical_sha256":"32c4dc06bd8b9687a4a785ca39bec4ab86529faf08236eb984ffc86550ccf99d","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"},"source_kind":"arxiv","source_id":"1603.08907","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wc3wjvjLcRdzsaksTmD0RDvaa+UwvdT6zotQ5kG25hH58bouMTUL1qKWgzg06uznmIt90tpEy2bm28SbjMHTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:08:31.380132Z"},"content_sha256":"973576078438d186835279c6498f772448a06efc7efac16e1590264c12300c68","schema_version":"1.0","event_id":"sha256:973576078438d186835279c6498f772448a06efc7efac16e1590264c12300c68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:GLCNYBV5ROLIPJFHQXFDTPWEVO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ITZb10Ym5EqHuEHfnghGH94VW/1Vl5nLhEPEM3F6TusewRFbdANqJ1F5D7Z9yV82ZKz7ckVjnP8rhYMJ/8CbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:08:31.380857Z"},"content_sha256":"92f8a2e9b75ac10f2156c5a2dfcebb832f13605dd519cd0346ee2612ebc6444a","schema_version":"1.0","event_id":"sha256:92f8a2e9b75ac10f2156c5a2dfcebb832f13605dd519cd0346ee2612ebc6444a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/bundle.json","state_url":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T21:08:31Z","links":{"resolver":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO","bundle":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/bundle.json","state":"https://pith.science/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GLCNYBV5ROLIPJFHQXFDTPWEVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:GLCNYBV5ROLIPJFHQXFDTPWEVO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2d652f762584773fa5faba0ce466c0056f7cc722b7795165956dc882f4410f4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-29T19:47:46Z","title_canon_sha256":"c9d6e6f25fb47122cd3b9a1a0aa36daab390d237729235fb158f39f8932b3f1b"},"schema_version":"1.0","source":{"id":"1603.08907","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.08907","created_at":"2026-05-18T01:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"1603.08907v1","created_at":"2026-05-18T01:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08907","created_at":"2026-05-18T01:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"GLCNYBV5ROLI","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GLCNYBV5ROLIPJFH","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GLCNYBV5","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:92f8a2e9b75ac10f2156c5a2dfcebb832f13605dd519cd0346ee2612ebc6444a","target":"graph","created_at":"2026-05-18T01:18:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Punarjay Chakravarty, Tinne Tuytelaars","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-29T19:47:46Z","title":"Cross-modal Supervision for Learning Active Speaker Detection in Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08907","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:973576078438d186835279c6498f772448a06efc7efac16e1590264c12300c68","target":"record","created_at":"2026-05-18T01:18:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2d652f762584773fa5faba0ce466c0056f7cc722b7795165956dc882f4410f4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-29T19:47:46Z","title_canon_sha256":"c9d6e6f25fb47122cd3b9a1a0aa36daab390d237729235fb158f39f8932b3f1b"},"schema_version":"1.0","source":{"id":"1603.08907","kind":"arxiv","version":1}},"canonical_sha256":"32c4dc06bd8b9687a4a785ca39bec4ab86529faf08236eb984ffc86550ccf99d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32c4dc06bd8b9687a4a785ca39bec4ab86529faf08236eb984ffc86550ccf99d","first_computed_at":"2026-05-18T01:18:04.996171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:18:04.996171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DkMjNXd9ywh8XAh6MWsCGEGzBi6ENGb97+XVIrbkuI4lDoh+aZQVyGSsuGg9mR/huushCxpWAZKmlrMXNVzUDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:18:04.996967Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.08907","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:973576078438d186835279c6498f772448a06efc7efac16e1590264c12300c68","sha256:92f8a2e9b75ac10f2156c5a2dfcebb832f13605dd519cd0346ee2612ebc6444a"],"state_sha256":"075d6a183d19c59def40112c7a83a67df8ee0176e7a8d5df1649a287305eead2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fY+g741gHIL9zyPHZni4BciwhWWUyf0QkkqFW0a3Om5vzFppl2gr16pBWJhW8uzj7iAIJ6m5BiTIZS1rs25CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T21:08:31.384535Z","bundle_sha256":"06529155fe80c4b6448e07f54f5bb531051b9def217c73525facae8513c9ce89"}}