{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7BOXSLVMWNNEKITRNRJUYY5ISH","short_pith_number":"pith:7BOXSLVM","schema_version":"1.0","canonical_sha256":"f85d792eacb35a4522716c534c63a891e06a96676fe11b4c6be2851ddcafe7ef","source":{"kind":"arxiv","id":"2607.28129","version":1},"attestation_state":"computed","paper":{"title":"Face and Voice Cross-modal Association with Learning Convex Feature Embedding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Jiwoo Kang, Taewan Kim","submitted_at":"2026-07-30T12:37:58Z","abstract_excerpt":"Face-and-voice association learning is one of the most challenging tasks in deep learning. In this paper, we propose a simple but powerful cross-modal feature embedding method for the association of faces and voices. Previous work has studied cross-modal association tasks to establish the correlation between voice clips and facial images. These works have addressed cross-modal discrimination but underestimate the importance of handling heterogeneity in inter-modal features between audio and video, resulting in a lot of false positives and false negatives. To tackle the problem, the proposed me"},"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":"2607.28129","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T12:37:58Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"355de476b6aa033957fa4d70e9c3eb5bb2399bf4a83888bb52168a0f61d1985f","abstract_canon_sha256":"05af4919c069df65362d8627947a8671db529efd2ab2cf68705c0dd9b74bd598"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85d792eacb35a4522716c534c63a891e06a96676fe11b4c6be2851ddcafe7ef","last_reissued_at":"2026-07-31T01:35:49.980184Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:49.980184Z"},"graph_snapshot":{"paper":{"title":"Face and Voice Cross-modal Association with Learning Convex Feature Embedding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Jiwoo Kang, Taewan Kim","submitted_at":"2026-07-30T12:37:58Z","abstract_excerpt":"Face-and-voice association learning is one of the most challenging tasks in deep learning. In this paper, we propose a simple but powerful cross-modal feature embedding method for the association of faces and voices. Previous work has studied cross-modal association tasks to establish the correlation between voice clips and facial images. These works have addressed cross-modal discrimination but underestimate the importance of handling heterogeneity in inter-modal features between audio and video, resulting in a lot of false positives and false negatives. To tackle the problem, the proposed me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28129","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.28129/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2607.28129","created_at":"2026-07-31T01:35:49.983261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28129v1","created_at":"2026-07-31T01:35:49.983261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28129","created_at":"2026-07-31T01:35:49.983261+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BOXSLVMWNNE","created_at":"2026-07-31T01:35:49.983261+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BOXSLVMWNNEKITR","created_at":"2026-07-31T01:35:49.983261+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BOXSLVM","created_at":"2026-07-31T01:35:49.983261+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/7BOXSLVMWNNEKITRNRJUYY5ISH","json":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH.json","graph_json":"https://pith.science/api/pith-number/7BOXSLVMWNNEKITRNRJUYY5ISH/graph.json","events_json":"https://pith.science/api/pith-number/7BOXSLVMWNNEKITRNRJUYY5ISH/events.json","paper":"https://pith.science/paper/7BOXSLVM"},"agent_actions":{"view_html":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH","download_json":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH.json","view_paper":"https://pith.science/paper/7BOXSLVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28129&json=true","fetch_graph":"https://pith.science/api/pith-number/7BOXSLVMWNNEKITRNRJUYY5ISH/graph.json","fetch_events":"https://pith.science/api/pith-number/7BOXSLVMWNNEKITRNRJUYY5ISH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/action/storage_attestation","attest_author":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/action/author_attestation","sign_citation":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/action/citation_signature","submit_replication":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/action/replication_record"}},"created_at":"2026-07-31T01:35:49.983261+00:00","updated_at":"2026-07-31T01:35:49.983261+00:00"}