{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:46FHERGSDTYPMEE3U27UQH6CLK","short_pith_number":"pith:46FHERGS","schema_version":"1.0","canonical_sha256":"e78a7244d21cf0f6109ba6bf481fc25a8a1aab895e4ab542ae7ae757c2ab6528","source":{"kind":"arxiv","id":"1811.10813","version":1},"attestation_state":"computed","paper":{"title":"Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"James Glass, Suwon Shon, Tae-Hyun Oh","submitted_at":"2018-11-27T04:58:10Z","abstract_excerpt":"In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the association of voice and face, we propose an attention-based end-to-end neural network that learns multi-sensory associations for the task of person verification. The attention mechanism in our proposed network learns to conditionally select a salient modality between speech and facial representations that provides a balance between complementary inputs. By virtue of this capability, the network is robust to missing or corrupted data from e"},"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":"1811.10813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T04:58:10Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f32365eb075b41178492aef19926779bee33764ccb236b24043f7b0a4dbf47fb","abstract_canon_sha256":"5cd27c3470a4c5bf3ef10382f8ee272044d66f96fbe3a62ece1e3b04af763bb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:47.485508Z","signature_b64":"f9c3p3UqPxif9UugBKhGIFahQvlLdlzMBrcJhxyhOIClo3O9/hNW5mBFfciajbCHhxI0AuGtkOyi5NyK7FT/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78a7244d21cf0f6109ba6bf481fc25a8a1aab895e4ab542ae7ae757c2ab6528","last_reissued_at":"2026-05-17T23:59:47.485025Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:47.485025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"James Glass, Suwon Shon, Tae-Hyun Oh","submitted_at":"2018-11-27T04:58:10Z","abstract_excerpt":"In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the association of voice and face, we propose an attention-based end-to-end neural network that learns multi-sensory associations for the task of person verification. The attention mechanism in our proposed network learns to conditionally select a salient modality between speech and facial representations that provides a balance between complementary inputs. By virtue of this capability, the network is robust to missing or corrupted data from e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10813","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":"1811.10813","created_at":"2026-05-17T23:59:47.485091+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10813v1","created_at":"2026-05-17T23:59:47.485091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10813","created_at":"2026-05-17T23:59:47.485091+00:00"},{"alias_kind":"pith_short_12","alias_value":"46FHERGSDTYP","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"46FHERGSDTYPMEE3","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"46FHERGS","created_at":"2026-05-18T12:32:05.422762+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/46FHERGSDTYPMEE3U27UQH6CLK","json":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK.json","graph_json":"https://pith.science/api/pith-number/46FHERGSDTYPMEE3U27UQH6CLK/graph.json","events_json":"https://pith.science/api/pith-number/46FHERGSDTYPMEE3U27UQH6CLK/events.json","paper":"https://pith.science/paper/46FHERGS"},"agent_actions":{"view_html":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK","download_json":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK.json","view_paper":"https://pith.science/paper/46FHERGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10813&json=true","fetch_graph":"https://pith.science/api/pith-number/46FHERGSDTYPMEE3U27UQH6CLK/graph.json","fetch_events":"https://pith.science/api/pith-number/46FHERGSDTYPMEE3U27UQH6CLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/action/storage_attestation","attest_author":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/action/author_attestation","sign_citation":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/action/citation_signature","submit_replication":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/action/replication_record"}},"created_at":"2026-05-17T23:59:47.485091+00:00","updated_at":"2026-05-17T23:59:47.485091+00:00"}