{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GTSINQOUBUMUE5WUZHH7T4CDTH","short_pith_number":"pith:GTSINQOU","schema_version":"1.0","canonical_sha256":"34e486c1d40d194276d4c9cff9f04399c831eef05e3aa2f69ea2df6d257a2572","source":{"kind":"arxiv","id":"2404.05466","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Wang, Huan Zhou, Lei Xie, Pengcheng Guo, Xucheng Wan","submitted_at":"2024-04-08T12:44:24Z","abstract_excerpt":"Automatic lip-reading (ALR) aims to automatically transcribe spoken content from a speaker's silent lip motion captured in video. Current mainstream lip-reading approaches only use a single visual encoder to model input videos of a single scale. In this paper, we propose to enhance lip-reading by incorporating multi-scale video data and multi-encoder. Specifically, we first propose a novel multi-scale lip motion extraction algorithm based on the size of the speaker's face and an Enhanced ResNet3D visual front-end (VFE) to extract lip features at different scales. For the multi-encoder, in addi"},"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":"2404.05466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T12:44:24Z","cross_cats_sorted":[],"title_canon_sha256":"6fe714656e78a7a29ee7929abad342afcc991e977c6cea0915f278d24de376f8","abstract_canon_sha256":"f840b20116b715107e567269f9ca68c917e250e04dee4ae2fa489a54bc3a74c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:54.051968Z","signature_b64":"VBpz8p1385bilL6PCcbzOIeS/qFJC8ioldyTv7WLOiC0K277mRsTW6x55qSTy/GfmsH6ue4wXh03r/316DfYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34e486c1d40d194276d4c9cff9f04399c831eef05e3aa2f69ea2df6d257a2572","last_reissued_at":"2026-07-05T08:13:54.051484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:54.051484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Wang, Huan Zhou, Lei Xie, Pengcheng Guo, Xucheng Wan","submitted_at":"2024-04-08T12:44:24Z","abstract_excerpt":"Automatic lip-reading (ALR) aims to automatically transcribe spoken content from a speaker's silent lip motion captured in video. Current mainstream lip-reading approaches only use a single visual encoder to model input videos of a single scale. In this paper, we propose to enhance lip-reading by incorporating multi-scale video data and multi-encoder. Specifically, we first propose a novel multi-scale lip motion extraction algorithm based on the size of the speaker's face and an Enhanced ResNet3D visual front-end (VFE) to extract lip features at different scales. For the multi-encoder, in addi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05466","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/2404.05466/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":"2404.05466","created_at":"2026-07-05T08:13:54.051541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05466v2","created_at":"2026-07-05T08:13:54.051541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05466","created_at":"2026-07-05T08:13:54.051541+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTSINQOUBUMU","created_at":"2026-07-05T08:13:54.051541+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTSINQOUBUMUE5WU","created_at":"2026-07-05T08:13:54.051541+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTSINQOU","created_at":"2026-07-05T08:13:54.051541+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/GTSINQOUBUMUE5WUZHH7T4CDTH","json":"https://pith.science/pith/GTSINQOUBUMUE5WUZHH7T4CDTH.json","graph_json":"https://pith.science/api/pith-number/GTSINQOUBUMUE5WUZHH7T4CDTH/graph.json","events_json":"https://pith.science/api/pith-number/GTSINQOUBUMUE5WUZHH7T4CDTH/events.json","paper":"https://pith.science/paper/GTSINQOU"},"agent_actions":{"view_html":"https://pith.science/pith/GTSINQOUBUMUE5WUZHH7T4CDTH","download_json":"https://pith.science/pith/GTSINQOUBUMUE5WUZHH7T4CDTH.json","view_paper":"https://pith.science/paper/GTSINQOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05466&json=true","fetch_graph":"https://pith.science/api/pith-number/GTSINQOUBUMUE5WUZHH7T4CDTH/graph.json","fetch_events":"https://pith.science/api/pith-number/GTSINQOUBUMUE5WUZHH7T4CDTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTSINQOUBUMUE5WUZHH7T4CDTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTSINQOUBUMUE5WUZHH7T4CDTH/action/storage_attestation","attest_author":"https://pith.science/pith/GTSINQOUBUMUE5WUZHH7T4CDTH/action/author_attestation","sign_citation":"https://pith.science/pith/GTSINQOUBUMUE5WUZHH7T4CDTH/action/citation_signature","submit_replication":"https://pith.science/pith/GTSINQOUBUMUE5WUZHH7T4CDTH/action/replication_record"}},"created_at":"2026-07-05T08:13:54.051541+00:00","updated_at":"2026-07-05T08:13:54.051541+00:00"}