{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TOQZFHQIXPLCVMK23SE4IWATTU","short_pith_number":"pith:TOQZFHQI","schema_version":"1.0","canonical_sha256":"9ba1929e08bbd62ab15adc89c458139d3868d46c9222f187cc6fec2a3ca31dc1","source":{"kind":"arxiv","id":"2506.13419","version":1},"attestation_state":"computed","paper":{"title":"Audio-Visual Driven Compression for Low-Bitrate Talking Head Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Jinjia Zhou, Riku Takahashi, Ryugo Morita","submitted_at":"2025-06-16T12:34:48Z","abstract_excerpt":"Talking head video compression has advanced with neural rendering and keypoint-based methods, but challenges remain, especially at low bit rates, including handling large head movements, suboptimal lip synchronization, and distorted facial reconstructions. To address these problems, we propose a novel audio-visual driven video codec that integrates compact 3D motion features and audio signals. This approach robustly models significant head rotations and aligns lip movements with speech, improving both compression efficiency and reconstruction quality. Experiments on the CelebV-HQ dataset show "},"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":"2506.13419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-06-16T12:34:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5a82b60fa07999674a47cac0c52a365ae96be162b95f45fd00065dbd73c4afcd","abstract_canon_sha256":"0c17d6755235845d3cfc4b2e0b6207b090537abd8161d8a9889e83cd1a3db6c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:10.122624Z","signature_b64":"OnZo9yvjBXE5H4jpuMqFwP2sOKdlp7hUBMDKiaol7IqslrOQQekjbrkD3cVt2AH8+GV+VPdNmxIA6/A2uY2FAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ba1929e08bbd62ab15adc89c458139d3868d46c9222f187cc6fec2a3ca31dc1","last_reissued_at":"2026-07-05T11:22:10.122201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:10.122201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Driven Compression for Low-Bitrate Talking Head Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Jinjia Zhou, Riku Takahashi, Ryugo Morita","submitted_at":"2025-06-16T12:34:48Z","abstract_excerpt":"Talking head video compression has advanced with neural rendering and keypoint-based methods, but challenges remain, especially at low bit rates, including handling large head movements, suboptimal lip synchronization, and distorted facial reconstructions. To address these problems, we propose a novel audio-visual driven video codec that integrates compact 3D motion features and audio signals. This approach robustly models significant head rotations and aligns lip movements with speech, improving both compression efficiency and reconstruction quality. Experiments on the CelebV-HQ dataset show "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13419","kind":"arxiv","version":1},"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/2506.13419/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":"2506.13419","created_at":"2026-07-05T11:22:10.122256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13419v1","created_at":"2026-07-05T11:22:10.122256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13419","created_at":"2026-07-05T11:22:10.122256+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOQZFHQIXPLC","created_at":"2026-07-05T11:22:10.122256+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOQZFHQIXPLCVMK2","created_at":"2026-07-05T11:22:10.122256+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOQZFHQI","created_at":"2026-07-05T11:22:10.122256+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/TOQZFHQIXPLCVMK23SE4IWATTU","json":"https://pith.science/pith/TOQZFHQIXPLCVMK23SE4IWATTU.json","graph_json":"https://pith.science/api/pith-number/TOQZFHQIXPLCVMK23SE4IWATTU/graph.json","events_json":"https://pith.science/api/pith-number/TOQZFHQIXPLCVMK23SE4IWATTU/events.json","paper":"https://pith.science/paper/TOQZFHQI"},"agent_actions":{"view_html":"https://pith.science/pith/TOQZFHQIXPLCVMK23SE4IWATTU","download_json":"https://pith.science/pith/TOQZFHQIXPLCVMK23SE4IWATTU.json","view_paper":"https://pith.science/paper/TOQZFHQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13419&json=true","fetch_graph":"https://pith.science/api/pith-number/TOQZFHQIXPLCVMK23SE4IWATTU/graph.json","fetch_events":"https://pith.science/api/pith-number/TOQZFHQIXPLCVMK23SE4IWATTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOQZFHQIXPLCVMK23SE4IWATTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOQZFHQIXPLCVMK23SE4IWATTU/action/storage_attestation","attest_author":"https://pith.science/pith/TOQZFHQIXPLCVMK23SE4IWATTU/action/author_attestation","sign_citation":"https://pith.science/pith/TOQZFHQIXPLCVMK23SE4IWATTU/action/citation_signature","submit_replication":"https://pith.science/pith/TOQZFHQIXPLCVMK23SE4IWATTU/action/replication_record"}},"created_at":"2026-07-05T11:22:10.122256+00:00","updated_at":"2026-07-05T11:22:10.122256+00:00"}