{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GTSINQOUBUMUE5WUZHH7T4CDTH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f840b20116b715107e567269f9ca68c917e250e04dee4ae2fa489a54bc3a74c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T12:44:24Z","title_canon_sha256":"6fe714656e78a7a29ee7929abad342afcc991e977c6cea0915f278d24de376f8"},"schema_version":"1.0","source":{"id":"2404.05466","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05466","created_at":"2026-07-05T08:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05466v2","created_at":"2026-07-05T08:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05466","created_at":"2026-07-05T08:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"GTSINQOUBUMU","created_at":"2026-07-05T08:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"GTSINQOUBUMUE5WU","created_at":"2026-07-05T08:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"GTSINQOU","created_at":"2026-07-05T08:13:54Z"}],"graph_snapshots":[{"event_id":"sha256:9d8e27f6df8134231bf4ec6f961d2e3d6bd275ebfa1e5e12cfc058278674b2bc","target":"graph","created_at":"2026-07-05T08:13:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.05466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"He Wang, Huan Zhou, Lei Xie, Pengcheng Guo, Xucheng Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T12:44:24Z","title":"Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05466","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:96cddafeb2eb9495ae10b707177ca58ce5e0b162c8bed14820f49728eae2d357","target":"record","created_at":"2026-07-05T08:13:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f840b20116b715107e567269f9ca68c917e250e04dee4ae2fa489a54bc3a74c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T12:44:24Z","title_canon_sha256":"6fe714656e78a7a29ee7929abad342afcc991e977c6cea0915f278d24de376f8"},"schema_version":"1.0","source":{"id":"2404.05466","kind":"arxiv","version":2}},"canonical_sha256":"34e486c1d40d194276d4c9cff9f04399c831eef05e3aa2f69ea2df6d257a2572","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34e486c1d40d194276d4c9cff9f04399c831eef05e3aa2f69ea2df6d257a2572","first_computed_at":"2026-07-05T08:13:54.051484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:54.051484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VBpz8p1385bilL6PCcbzOIeS/qFJC8ioldyTv7WLOiC0K277mRsTW6x55qSTy/GfmsH6ue4wXh03r/316DfYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:54.051968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05466","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96cddafeb2eb9495ae10b707177ca58ce5e0b162c8bed14820f49728eae2d357","sha256:9d8e27f6df8134231bf4ec6f961d2e3d6bd275ebfa1e5e12cfc058278674b2bc"],"state_sha256":"a1b1849588c13c090a7f536786c41bf6666eee17ab778a5e5ad6c1413e8f834b"}