{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:E5ZVAIUXUPU3A6QUK7L5FWWMCR","short_pith_number":"pith:E5ZVAIUX","schema_version":"1.0","canonical_sha256":"2773502297a3e9b07a1457d7d2dacc14643b3b5177f715bad133a80a211a5ca1","source":{"kind":"arxiv","id":"1602.04364","version":1},"attestation_state":"computed","paper":{"title":"Look, Listen and Learn - A Multimodal LSTM for Speaker Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Wang, Jimmy Ren, Li Xu, Qiong Yan, Wenxiu Sun, Yongtao Hu, Yu-Wing Tai","submitted_at":"2016-02-13T18:49:50Z","abstract_excerpt":"Speaker identification refers to the task of localizing the face of a person who has the same identity as the ongoing voice in a video. This task not only requires collective perception over both visual and auditory signals, the robustness to handle severe quality degradations and unconstrained content variations are also indispensable. In this paper, we describe a novel multimodal Long Short-Term Memory (LSTM) architecture which seamlessly unifies both visual and auditory modalities from the beginning of each sequence input. The key idea is to extend the conventional LSTM by not only sharing "},"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":"1602.04364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-13T18:49:50Z","cross_cats_sorted":[],"title_canon_sha256":"1a3843e5975ee43d9839baca15cee1553e92abde2d0a8449b0d3c79ad58fe5c3","abstract_canon_sha256":"5e68e610ff4e28a11395253f6fce1197260c66d3ba76ddea551371d05cddab41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:51.103329Z","signature_b64":"IFfTaOQrthncfXtFXbThoxcvSXZR2PGa7g/ybCo9KaarsJDCp3TvAqGlsMu12aeHVEoVy213pxSRrwEu2wP7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2773502297a3e9b07a1457d7d2dacc14643b3b5177f715bad133a80a211a5ca1","last_reissued_at":"2026-05-18T01:20:51.102719Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:51.102719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Look, Listen and Learn - A Multimodal LSTM for Speaker Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Wang, Jimmy Ren, Li Xu, Qiong Yan, Wenxiu Sun, Yongtao Hu, Yu-Wing Tai","submitted_at":"2016-02-13T18:49:50Z","abstract_excerpt":"Speaker identification refers to the task of localizing the face of a person who has the same identity as the ongoing voice in a video. This task not only requires collective perception over both visual and auditory signals, the robustness to handle severe quality degradations and unconstrained content variations are also indispensable. In this paper, we describe a novel multimodal Long Short-Term Memory (LSTM) architecture which seamlessly unifies both visual and auditory modalities from the beginning of each sequence input. The key idea is to extend the conventional LSTM by not only sharing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.04364","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":"1602.04364","created_at":"2026-05-18T01:20:51.102813+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.04364v1","created_at":"2026-05-18T01:20:51.102813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.04364","created_at":"2026-05-18T01:20:51.102813+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5ZVAIUXUPU3","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5ZVAIUXUPU3A6QU","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5ZVAIUX","created_at":"2026-05-18T12:30:12.583610+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/E5ZVAIUXUPU3A6QUK7L5FWWMCR","json":"https://pith.science/pith/E5ZVAIUXUPU3A6QUK7L5FWWMCR.json","graph_json":"https://pith.science/api/pith-number/E5ZVAIUXUPU3A6QUK7L5FWWMCR/graph.json","events_json":"https://pith.science/api/pith-number/E5ZVAIUXUPU3A6QUK7L5FWWMCR/events.json","paper":"https://pith.science/paper/E5ZVAIUX"},"agent_actions":{"view_html":"https://pith.science/pith/E5ZVAIUXUPU3A6QUK7L5FWWMCR","download_json":"https://pith.science/pith/E5ZVAIUXUPU3A6QUK7L5FWWMCR.json","view_paper":"https://pith.science/paper/E5ZVAIUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.04364&json=true","fetch_graph":"https://pith.science/api/pith-number/E5ZVAIUXUPU3A6QUK7L5FWWMCR/graph.json","fetch_events":"https://pith.science/api/pith-number/E5ZVAIUXUPU3A6QUK7L5FWWMCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5ZVAIUXUPU3A6QUK7L5FWWMCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5ZVAIUXUPU3A6QUK7L5FWWMCR/action/storage_attestation","attest_author":"https://pith.science/pith/E5ZVAIUXUPU3A6QUK7L5FWWMCR/action/author_attestation","sign_citation":"https://pith.science/pith/E5ZVAIUXUPU3A6QUK7L5FWWMCR/action/citation_signature","submit_replication":"https://pith.science/pith/E5ZVAIUXUPU3A6QUK7L5FWWMCR/action/replication_record"}},"created_at":"2026-05-18T01:20:51.102813+00:00","updated_at":"2026-05-18T01:20:51.102813+00:00"}