{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LNTRI6ZN5NXWN3GUB6UJRB7EBJ","short_pith_number":"pith:LNTRI6ZN","schema_version":"1.0","canonical_sha256":"5b67147b2deb6f66ecd40fa89887e40a7d6ab98240a555722c1d6b5e07f67276","source":{"kind":"arxiv","id":"2205.14295","version":2},"attestation_state":"computed","paper":{"title":"Is Lip Region-of-Interest Sufficient for Lipreading?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"Gen-Shun Wan, Jia Pan, Jing-Xuan Zhang","submitted_at":"2022-05-28T01:34:24Z","abstract_excerpt":"Lip region-of-interest (ROI) is conventionally used for visual input in the lipreading task. Few works have adopted the entire face as visual input because lip-excluded parts of the face are usually considered to be redundant and irrelevant to visual speech recognition. However, faces contain much more detailed information than lips, such as speakers' head pose, emotion, identity etc. We argue that such information might benefit visual speech recognition if a powerful feature extractor employing the entire face is trained. In this work, we propose to adopt the entire face for lipreading with s"},"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":"2205.14295","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-28T01:34:24Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0d2c1c2012c2ab9aabf334c03159a538b4c2cb022a068a7410db90a23dff1dfe","abstract_canon_sha256":"fba1dd0a3c00dc6fd759c15c06a207e4f2df159455cc9eddb7c23051e6c75ee9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:32.010072Z","signature_b64":"CSrVTKAVH0om6fv3AJGJoXRJzqco7w7u0WkSQDaEBB+ovp7aV7fGONrlZEuXiLQMfi/UkK6v9umEEAvkWSy6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b67147b2deb6f66ecd40fa89887e40a7d6ab98240a555722c1d6b5e07f67276","last_reissued_at":"2026-07-05T04:28:32.009502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:32.009502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Lip Region-of-Interest Sufficient for Lipreading?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"Gen-Shun Wan, Jia Pan, Jing-Xuan Zhang","submitted_at":"2022-05-28T01:34:24Z","abstract_excerpt":"Lip region-of-interest (ROI) is conventionally used for visual input in the lipreading task. Few works have adopted the entire face as visual input because lip-excluded parts of the face are usually considered to be redundant and irrelevant to visual speech recognition. However, faces contain much more detailed information than lips, such as speakers' head pose, emotion, identity etc. We argue that such information might benefit visual speech recognition if a powerful feature extractor employing the entire face is trained. In this work, we propose to adopt the entire face for lipreading with s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14295","kind":"arxiv","version":2},"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/2205.14295/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":"2205.14295","created_at":"2026-07-05T04:28:32.009561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14295v2","created_at":"2026-07-05T04:28:32.009561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14295","created_at":"2026-07-05T04:28:32.009561+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNTRI6ZN5NXW","created_at":"2026-07-05T04:28:32.009561+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNTRI6ZN5NXWN3GU","created_at":"2026-07-05T04:28:32.009561+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNTRI6ZN","created_at":"2026-07-05T04:28:32.009561+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/LNTRI6ZN5NXWN3GUB6UJRB7EBJ","json":"https://pith.science/pith/LNTRI6ZN5NXWN3GUB6UJRB7EBJ.json","graph_json":"https://pith.science/api/pith-number/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/graph.json","events_json":"https://pith.science/api/pith-number/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/events.json","paper":"https://pith.science/paper/LNTRI6ZN"},"agent_actions":{"view_html":"https://pith.science/pith/LNTRI6ZN5NXWN3GUB6UJRB7EBJ","download_json":"https://pith.science/pith/LNTRI6ZN5NXWN3GUB6UJRB7EBJ.json","view_paper":"https://pith.science/paper/LNTRI6ZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14295&json=true","fetch_graph":"https://pith.science/api/pith-number/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/action/storage_attestation","attest_author":"https://pith.science/pith/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/action/author_attestation","sign_citation":"https://pith.science/pith/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/action/citation_signature","submit_replication":"https://pith.science/pith/LNTRI6ZN5NXWN3GUB6UJRB7EBJ/action/replication_record"}},"created_at":"2026-07-05T04:28:32.009561+00:00","updated_at":"2026-07-05T04:28:32.009561+00:00"}