{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3HVYGLVOR7U7XVZKB5DG5AAVHA","short_pith_number":"pith:3HVYGLVO","schema_version":"1.0","canonical_sha256":"d9eb832eae8fe9fbd72a0f466e80153814a96cc206988d3dd2f0b21b68855f54","source":{"kind":"arxiv","id":"1809.08761","version":1},"attestation_state":"computed","paper":{"title":"Speaker Naming in Movies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jia Deng, Mahmoud Azab, Max Smith, Mingzhe Wang, Noriyuki Kojima, Rada Mihalcea","submitted_at":"2018-09-24T05:00:05Z","abstract_excerpt":"We propose a new model for speaker naming in movies that leverages visual, textual, and acoustic modalities in an unified optimization framework. To evaluate the performance of our model, we introduce a new dataset consisting of six episodes of the Big Bang Theory TV show and eighteen full movies covering different genres. Our experiments show that our multimodal model significantly outperforms several competitive baselines on the average weighted F-score metric. To demonstrate the effectiveness of our framework, we design an end-to-end memory network model that leverages our speaker naming mo"},"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":"1809.08761","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-24T05:00:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"99ec91e694d16c8c2993ed680d8ae4d685963cecc8d5e2f6353118a7d53c3375","abstract_canon_sha256":"8a796d474d1e3f3779ce13ec9f75d6eac318df7b5b2a57bb5604eb4cd23994b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:03.642686Z","signature_b64":"wBIcdH+xDX37yplq+odhIthlf7N5q4UTAk885B7gqthcgrSh//VmwixroUaKmFckZY0PRYfqB7Pa3SmC50fTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9eb832eae8fe9fbd72a0f466e80153814a96cc206988d3dd2f0b21b68855f54","last_reissued_at":"2026-05-18T00:05:03.642049Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:03.642049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker Naming in Movies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jia Deng, Mahmoud Azab, Max Smith, Mingzhe Wang, Noriyuki Kojima, Rada Mihalcea","submitted_at":"2018-09-24T05:00:05Z","abstract_excerpt":"We propose a new model for speaker naming in movies that leverages visual, textual, and acoustic modalities in an unified optimization framework. To evaluate the performance of our model, we introduce a new dataset consisting of six episodes of the Big Bang Theory TV show and eighteen full movies covering different genres. Our experiments show that our multimodal model significantly outperforms several competitive baselines on the average weighted F-score metric. To demonstrate the effectiveness of our framework, we design an end-to-end memory network model that leverages our speaker naming mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08761","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":"1809.08761","created_at":"2026-05-18T00:05:03.642174+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.08761v1","created_at":"2026-05-18T00:05:03.642174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08761","created_at":"2026-05-18T00:05:03.642174+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HVYGLVOR7U7","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HVYGLVOR7U7XVZK","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HVYGLVO","created_at":"2026-05-18T12:32:02.567920+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/3HVYGLVOR7U7XVZKB5DG5AAVHA","json":"https://pith.science/pith/3HVYGLVOR7U7XVZKB5DG5AAVHA.json","graph_json":"https://pith.science/api/pith-number/3HVYGLVOR7U7XVZKB5DG5AAVHA/graph.json","events_json":"https://pith.science/api/pith-number/3HVYGLVOR7U7XVZKB5DG5AAVHA/events.json","paper":"https://pith.science/paper/3HVYGLVO"},"agent_actions":{"view_html":"https://pith.science/pith/3HVYGLVOR7U7XVZKB5DG5AAVHA","download_json":"https://pith.science/pith/3HVYGLVOR7U7XVZKB5DG5AAVHA.json","view_paper":"https://pith.science/paper/3HVYGLVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.08761&json=true","fetch_graph":"https://pith.science/api/pith-number/3HVYGLVOR7U7XVZKB5DG5AAVHA/graph.json","fetch_events":"https://pith.science/api/pith-number/3HVYGLVOR7U7XVZKB5DG5AAVHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HVYGLVOR7U7XVZKB5DG5AAVHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HVYGLVOR7U7XVZKB5DG5AAVHA/action/storage_attestation","attest_author":"https://pith.science/pith/3HVYGLVOR7U7XVZKB5DG5AAVHA/action/author_attestation","sign_citation":"https://pith.science/pith/3HVYGLVOR7U7XVZKB5DG5AAVHA/action/citation_signature","submit_replication":"https://pith.science/pith/3HVYGLVOR7U7XVZKB5DG5AAVHA/action/replication_record"}},"created_at":"2026-05-18T00:05:03.642174+00:00","updated_at":"2026-05-18T00:05:03.642174+00:00"}