{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LAHIB66NMZQP5LS7EOWFUEHOPK","short_pith_number":"pith:LAHIB66N","schema_version":"1.0","canonical_sha256":"580e80fbcd6660feae5f23ac5a10ee7a8a229fb9c53c02a5e328d9ec954125de","source":{"kind":"arxiv","id":"2005.08606","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Lip Synchronisation Based on Pattern Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bong-Jin Lee, Hee Soo Heo, Soo-Whan Chung, You Jin Kim","submitted_at":"2020-05-18T11:42:32Z","abstract_excerpt":"The goal of this work is to synchronise audio and video of a talking face using deep neural network models. Existing works have trained networks on proxy tasks such as cross-modal similarity learning, and then computed similarities between audio and video frames using a sliding window approach. While these methods demonstrate satisfactory performance, the networks are not trained directly on the task. To this end, we propose an end-to-end trained network that can directly predict the offset between an audio stream and the corresponding video stream. The similarity matrix between the two modali"},"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":"2005.08606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-18T11:42:32Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"ef7febf5b1686225fe16c168044bc2459d4a8e0c78277cb0f406b1eecd47433e","abstract_canon_sha256":"c58fb2cd55f2bd53771a935298159a8dd22112571bfe6ebbc30ba187806e6a12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:29.169166Z","signature_b64":"yJP3lS6awkypD34FBzg07JeM838zAuKvmQcM6ylaxOQKyw5IqJfOP4JElwnAktQkQW7aCGIpHQQQkO3nW7GKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"580e80fbcd6660feae5f23ac5a10ee7a8a229fb9c53c02a5e328d9ec954125de","last_reissued_at":"2026-07-05T02:24:29.168758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:29.168758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Lip Synchronisation Based on Pattern Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bong-Jin Lee, Hee Soo Heo, Soo-Whan Chung, You Jin Kim","submitted_at":"2020-05-18T11:42:32Z","abstract_excerpt":"The goal of this work is to synchronise audio and video of a talking face using deep neural network models. Existing works have trained networks on proxy tasks such as cross-modal similarity learning, and then computed similarities between audio and video frames using a sliding window approach. While these methods demonstrate satisfactory performance, the networks are not trained directly on the task. To this end, we propose an end-to-end trained network that can directly predict the offset between an audio stream and the corresponding video stream. The similarity matrix between the two modali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08606","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/2005.08606/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":"2005.08606","created_at":"2026-07-05T02:24:29.168822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.08606v2","created_at":"2026-07-05T02:24:29.168822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08606","created_at":"2026-07-05T02:24:29.168822+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAHIB66NMZQP","created_at":"2026-07-05T02:24:29.168822+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAHIB66NMZQP5LS7","created_at":"2026-07-05T02:24:29.168822+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAHIB66N","created_at":"2026-07-05T02:24:29.168822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03222","citing_title":"The role of gain neuromodulation in layer-5 pyramidal neurons","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK","json":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK.json","graph_json":"https://pith.science/api/pith-number/LAHIB66NMZQP5LS7EOWFUEHOPK/graph.json","events_json":"https://pith.science/api/pith-number/LAHIB66NMZQP5LS7EOWFUEHOPK/events.json","paper":"https://pith.science/paper/LAHIB66N"},"agent_actions":{"view_html":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK","download_json":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK.json","view_paper":"https://pith.science/paper/LAHIB66N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.08606&json=true","fetch_graph":"https://pith.science/api/pith-number/LAHIB66NMZQP5LS7EOWFUEHOPK/graph.json","fetch_events":"https://pith.science/api/pith-number/LAHIB66NMZQP5LS7EOWFUEHOPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK/action/storage_attestation","attest_author":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK/action/author_attestation","sign_citation":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK/action/citation_signature","submit_replication":"https://pith.science/pith/LAHIB66NMZQP5LS7EOWFUEHOPK/action/replication_record"}},"created_at":"2026-07-05T02:24:29.168822+00:00","updated_at":"2026-07-05T02:24:29.168822+00:00"}