{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A6LFS6QD4VK57DBIHX3G43BH2W","short_pith_number":"pith:A6LFS6QD","schema_version":"1.0","canonical_sha256":"0796597a03e555df8c283df66e6c27d5928a4ede6e6fee93fb937def771c6fb8","source":{"kind":"arxiv","id":"2404.11979","version":2},"attestation_state":"computed","paper":{"title":"MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jialie Shen, Jun Wang, Lei Yu, Wei Yu, Wenhao Zhang, Yong Luo, Zheng He","submitted_at":"2024-04-18T08:16:56Z","abstract_excerpt":"Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel"},"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":"2404.11979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T08:16:56Z","cross_cats_sorted":[],"title_canon_sha256":"f6267834e32c69d5f0dc1bff06abbdcd64b65aa8b5e61b3148b92a70d5b119e8","abstract_canon_sha256":"66cf3e682b6493603aa8f5d12a38e67a9e66601b48d46a04d9de285c82619d9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:28.216005Z","signature_b64":"+XL150HSdlmdwpOp/CR8MSFB5+3mvgn8nLCPw0ejjk307iKKz722m56AiXfDknuLoOGMY9/tAtY88/Xd0fZSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0796597a03e555df8c283df66e6c27d5928a4ede6e6fee93fb937def771c6fb8","last_reissued_at":"2026-07-05T10:47:28.215510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:28.215510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jialie Shen, Jun Wang, Lei Yu, Wei Yu, Wenhao Zhang, Yong Luo, Zheng He","submitted_at":"2024-04-18T08:16:56Z","abstract_excerpt":"Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11979","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/2404.11979/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":"2404.11979","created_at":"2026-07-05T10:47:28.215567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11979v2","created_at":"2026-07-05T10:47:28.215567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11979","created_at":"2026-07-05T10:47:28.215567+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6LFS6QD4VK5","created_at":"2026-07-05T10:47:28.215567+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6LFS6QD4VK57DBI","created_at":"2026-07-05T10:47:28.215567+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6LFS6QD","created_at":"2026-07-05T10:47:28.215567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04817","citing_title":"Spike-TBR: a Noise Resilient Neuromorphic Event Representation","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W","json":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W.json","graph_json":"https://pith.science/api/pith-number/A6LFS6QD4VK57DBIHX3G43BH2W/graph.json","events_json":"https://pith.science/api/pith-number/A6LFS6QD4VK57DBIHX3G43BH2W/events.json","paper":"https://pith.science/paper/A6LFS6QD"},"agent_actions":{"view_html":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W","download_json":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W.json","view_paper":"https://pith.science/paper/A6LFS6QD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11979&json=true","fetch_graph":"https://pith.science/api/pith-number/A6LFS6QD4VK57DBIHX3G43BH2W/graph.json","fetch_events":"https://pith.science/api/pith-number/A6LFS6QD4VK57DBIHX3G43BH2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W/action/storage_attestation","attest_author":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W/action/author_attestation","sign_citation":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W/action/citation_signature","submit_replication":"https://pith.science/pith/A6LFS6QD4VK57DBIHX3G43BH2W/action/replication_record"}},"created_at":"2026-07-05T10:47:28.215567+00:00","updated_at":"2026-07-05T10:47:28.215567+00:00"}