{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3SA7BIIWKAU6A3NML44OIKDE4U","short_pith_number":"pith:3SA7BIIW","schema_version":"1.0","canonical_sha256":"dc81f0a1165029e06dac5f38e42864e53aa95a7fdc63e02747d184db6a072fd5","source":{"kind":"arxiv","id":"2403.06421","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Study of Perceptual Quality Metrics for Audio-driven Talking Head Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengguang Zhu, Guangtao Zhai, Jingnan Gao, Weixia Zhang, Xiaokang Yang, Yichao Yan","submitted_at":"2024-03-11T04:13:38Z","abstract_excerpt":"The rapid advancement of Artificial Intelligence Generated Content (AIGC) technology has propelled audio-driven talking head generation, gaining considerable research attention for practical applications. However, performance evaluation research lags behind the development of talking head generation techniques. Existing literature relies on heuristic quantitative metrics without human validation, hindering accurate progress assessment. To address this gap, we collect talking head videos generated from four generative methods and conduct controlled psychophysical experiments on visual quality, "},"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":"2403.06421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T04:13:38Z","cross_cats_sorted":[],"title_canon_sha256":"77315f5318a86749df2176994a56661c372e339cb7432f4553c2c53bf8ea0a38","abstract_canon_sha256":"c3c2288f283a5f924e8044727b3090200a2c2b273107e62597ef4958fd55dde6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:37.860013Z","signature_b64":"61lHFvyAdkoBcaImkwiN+fYPqx0e+M9+eLwHCEW+5Oj8+kiQsQuoEbJSWUUg94rt7VcStSV7Rjh00D5fWMBEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc81f0a1165029e06dac5f38e42864e53aa95a7fdc63e02747d184db6a072fd5","last_reissued_at":"2026-07-05T07:54:37.859523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:37.859523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study of Perceptual Quality Metrics for Audio-driven Talking Head Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengguang Zhu, Guangtao Zhai, Jingnan Gao, Weixia Zhang, Xiaokang Yang, Yichao Yan","submitted_at":"2024-03-11T04:13:38Z","abstract_excerpt":"The rapid advancement of Artificial Intelligence Generated Content (AIGC) technology has propelled audio-driven talking head generation, gaining considerable research attention for practical applications. However, performance evaluation research lags behind the development of talking head generation techniques. Existing literature relies on heuristic quantitative metrics without human validation, hindering accurate progress assessment. To address this gap, we collect talking head videos generated from four generative methods and conduct controlled psychophysical experiments on visual quality, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06421","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/2403.06421/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":"2403.06421","created_at":"2026-07-05T07:54:37.859581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06421v1","created_at":"2026-07-05T07:54:37.859581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06421","created_at":"2026-07-05T07:54:37.859581+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SA7BIIWKAU6","created_at":"2026-07-05T07:54:37.859581+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SA7BIIWKAU6A3NM","created_at":"2026-07-05T07:54:37.859581+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SA7BIIW","created_at":"2026-07-05T07:54:37.859581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09268","citing_title":"LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U","json":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U.json","graph_json":"https://pith.science/api/pith-number/3SA7BIIWKAU6A3NML44OIKDE4U/graph.json","events_json":"https://pith.science/api/pith-number/3SA7BIIWKAU6A3NML44OIKDE4U/events.json","paper":"https://pith.science/paper/3SA7BIIW"},"agent_actions":{"view_html":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U","download_json":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U.json","view_paper":"https://pith.science/paper/3SA7BIIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06421&json=true","fetch_graph":"https://pith.science/api/pith-number/3SA7BIIWKAU6A3NML44OIKDE4U/graph.json","fetch_events":"https://pith.science/api/pith-number/3SA7BIIWKAU6A3NML44OIKDE4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U/action/storage_attestation","attest_author":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U/action/author_attestation","sign_citation":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U/action/citation_signature","submit_replication":"https://pith.science/pith/3SA7BIIWKAU6A3NML44OIKDE4U/action/replication_record"}},"created_at":"2026-07-05T07:54:37.859581+00:00","updated_at":"2026-07-05T07:54:37.859581+00:00"}