{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MP4GBDINTOPYWE2EA2ABJ6PC25","short_pith_number":"pith:MP4GBDIN","schema_version":"1.0","canonical_sha256":"63f8608d0d9b9f8b1344068014f9e2d768dc9b7237a6b9c8bdb00cbbfafe4cf5","source":{"kind":"arxiv","id":"1804.00326","version":2},"attestation_state":"computed","paper":{"title":"Seeing Voices and Hearing Faces: Cross-modal biometric matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Samuel Albanie","submitted_at":"2018-04-01T18:02:41Z","abstract_excerpt":"We introduce a seemingly impossible task: given only an audio clip of someone speaking, decide which of two face images is the speaker. In this paper we study this, and a number of related cross-modal tasks, aimed at answering the question: how much can we infer from the voice about the face and vice versa? We study this task \"in the wild\", employing the datasets that are now publicly available for face recognition from static images (VGGFace) and speaker identification from audio (VoxCeleb). These provide training and testing scenarios for both static and dynamic testing of cross-modal matchi"},"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":"1804.00326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-01T18:02:41Z","cross_cats_sorted":[],"title_canon_sha256":"e08909275751ae41549eba40990b67306cdd0ddff4c4e64f0065abd25aa685b5","abstract_canon_sha256":"1a8c30b16fdeb9baab5e562d5e1a319386e9bf6a626c50abf944e4d9fbce4f93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:32.541044Z","signature_b64":"goGsaWO7CiWhjHJLqoVEl/YtrhnCvqNnMmxFZNXq5RcTQUtJ8XpgQ5xObhKBEYdOtgoSv+VUl+h2tWpSkhHLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63f8608d0d9b9f8b1344068014f9e2d768dc9b7237a6b9c8bdb00cbbfafe4cf5","last_reissued_at":"2026-05-18T00:19:32.540518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:32.540518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing Voices and Hearing Faces: Cross-modal biometric matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Samuel Albanie","submitted_at":"2018-04-01T18:02:41Z","abstract_excerpt":"We introduce a seemingly impossible task: given only an audio clip of someone speaking, decide which of two face images is the speaker. In this paper we study this, and a number of related cross-modal tasks, aimed at answering the question: how much can we infer from the voice about the face and vice versa? We study this task \"in the wild\", employing the datasets that are now publicly available for face recognition from static images (VGGFace) and speaker identification from audio (VoxCeleb). These provide training and testing scenarios for both static and dynamic testing of cross-modal matchi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00326","kind":"arxiv","version":2},"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":"1804.00326","created_at":"2026-05-18T00:19:32.540604+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.00326v2","created_at":"2026-05-18T00:19:32.540604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00326","created_at":"2026-05-18T00:19:32.540604+00:00"},{"alias_kind":"pith_short_12","alias_value":"MP4GBDINTOPY","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MP4GBDINTOPYWE2E","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MP4GBDIN","created_at":"2026-05-18T12:32:37.024351+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/MP4GBDINTOPYWE2EA2ABJ6PC25","json":"https://pith.science/pith/MP4GBDINTOPYWE2EA2ABJ6PC25.json","graph_json":"https://pith.science/api/pith-number/MP4GBDINTOPYWE2EA2ABJ6PC25/graph.json","events_json":"https://pith.science/api/pith-number/MP4GBDINTOPYWE2EA2ABJ6PC25/events.json","paper":"https://pith.science/paper/MP4GBDIN"},"agent_actions":{"view_html":"https://pith.science/pith/MP4GBDINTOPYWE2EA2ABJ6PC25","download_json":"https://pith.science/pith/MP4GBDINTOPYWE2EA2ABJ6PC25.json","view_paper":"https://pith.science/paper/MP4GBDIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.00326&json=true","fetch_graph":"https://pith.science/api/pith-number/MP4GBDINTOPYWE2EA2ABJ6PC25/graph.json","fetch_events":"https://pith.science/api/pith-number/MP4GBDINTOPYWE2EA2ABJ6PC25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MP4GBDINTOPYWE2EA2ABJ6PC25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MP4GBDINTOPYWE2EA2ABJ6PC25/action/storage_attestation","attest_author":"https://pith.science/pith/MP4GBDINTOPYWE2EA2ABJ6PC25/action/author_attestation","sign_citation":"https://pith.science/pith/MP4GBDINTOPYWE2EA2ABJ6PC25/action/citation_signature","submit_replication":"https://pith.science/pith/MP4GBDINTOPYWE2EA2ABJ6PC25/action/replication_record"}},"created_at":"2026-05-18T00:19:32.540604+00:00","updated_at":"2026-05-18T00:19:32.540604+00:00"}