{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5YAD7VBZVEWO7ZCH7HGBJE3UHF","short_pith_number":"pith:5YAD7VBZ","schema_version":"1.0","canonical_sha256":"ee003fd439a92cefe447f9cc1493743952dd232acdc5fc086ca3159f2c07f66a","source":{"kind":"arxiv","id":"2606.00751","version":1},"attestation_state":"computed","paper":{"title":"Head-Pose-Aware Visual Speech Recognition with FiLM Modulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibo Zhang, Matthew Kit Khinn Teng, Takeshi Saitoh","submitted_at":"2026-05-30T14:35:47Z","abstract_excerpt":"Visual Speech Recognition (VSR) aims to recognize speech from visual cues such as lip movements, but its performance is fundamentally limited by viseme ambiguity and pose-induced variations that introduce geometric distortions and occlusions. Existing approaches mainly rely on linguistic context or implicit invariance, leaving visual representations insufficiently robust under non-frontal views. In this work, we propose a pose-aware phoneme-level framework, termed HP-VSR-ResFiLM, that explicitly incorporates head-pose information into visual feature extraction. The proposed framework adopts a "},"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":"2606.00751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T14:35:47Z","cross_cats_sorted":[],"title_canon_sha256":"37775ff2318d152d3615a6372359d0cd398c31610c458e0dc6807506bba22b3a","abstract_canon_sha256":"b9c250e7055c9502e674b1a4f98533ceb665650abb6db4bf7d18060dbb04f173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:04.776422Z","signature_b64":"LZPm5t2QpUrCoKasTj1b1BD7YvakCfLj4/zSVtBHXLH4R4Jx/G6/60Uy6c1PdojjUV9C174DTcx4vkSAhsHKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee003fd439a92cefe447f9cc1493743952dd232acdc5fc086ca3159f2c07f66a","last_reissued_at":"2026-06-02T01:04:04.776064Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:04.776064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Head-Pose-Aware Visual Speech Recognition with FiLM Modulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibo Zhang, Matthew Kit Khinn Teng, Takeshi Saitoh","submitted_at":"2026-05-30T14:35:47Z","abstract_excerpt":"Visual Speech Recognition (VSR) aims to recognize speech from visual cues such as lip movements, but its performance is fundamentally limited by viseme ambiguity and pose-induced variations that introduce geometric distortions and occlusions. Existing approaches mainly rely on linguistic context or implicit invariance, leaving visual representations insufficiently robust under non-frontal views. In this work, we propose a pose-aware phoneme-level framework, termed HP-VSR-ResFiLM, that explicitly incorporates head-pose information into visual feature extraction. The proposed framework adopts a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00751","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/2606.00751/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":"2606.00751","created_at":"2026-06-02T01:04:04.776127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00751v1","created_at":"2026-06-02T01:04:04.776127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00751","created_at":"2026-06-02T01:04:04.776127+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YAD7VBZVEWO","created_at":"2026-06-02T01:04:04.776127+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YAD7VBZVEWO7ZCH","created_at":"2026-06-02T01:04:04.776127+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YAD7VBZ","created_at":"2026-06-02T01:04:04.776127+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/5YAD7VBZVEWO7ZCH7HGBJE3UHF","json":"https://pith.science/pith/5YAD7VBZVEWO7ZCH7HGBJE3UHF.json","graph_json":"https://pith.science/api/pith-number/5YAD7VBZVEWO7ZCH7HGBJE3UHF/graph.json","events_json":"https://pith.science/api/pith-number/5YAD7VBZVEWO7ZCH7HGBJE3UHF/events.json","paper":"https://pith.science/paper/5YAD7VBZ"},"agent_actions":{"view_html":"https://pith.science/pith/5YAD7VBZVEWO7ZCH7HGBJE3UHF","download_json":"https://pith.science/pith/5YAD7VBZVEWO7ZCH7HGBJE3UHF.json","view_paper":"https://pith.science/paper/5YAD7VBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00751&json=true","fetch_graph":"https://pith.science/api/pith-number/5YAD7VBZVEWO7ZCH7HGBJE3UHF/graph.json","fetch_events":"https://pith.science/api/pith-number/5YAD7VBZVEWO7ZCH7HGBJE3UHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YAD7VBZVEWO7ZCH7HGBJE3UHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YAD7VBZVEWO7ZCH7HGBJE3UHF/action/storage_attestation","attest_author":"https://pith.science/pith/5YAD7VBZVEWO7ZCH7HGBJE3UHF/action/author_attestation","sign_citation":"https://pith.science/pith/5YAD7VBZVEWO7ZCH7HGBJE3UHF/action/citation_signature","submit_replication":"https://pith.science/pith/5YAD7VBZVEWO7ZCH7HGBJE3UHF/action/replication_record"}},"created_at":"2026-06-02T01:04:04.776127+00:00","updated_at":"2026-06-02T01:04:04.776127+00:00"}