{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:18:54Z","timestamp":1778786334065,"version":"3.51.4"},"reference-count":79,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01134","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12201-12211","source":"Crossref","is-referenced-by-count":2,"title":["Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads"],"prefix":"10.1109","author":[{"given":"Yingjie","family":"Zhou","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiezhang","family":"Cao","sequence":"additional","affiliation":[{"name":"Harvard Medical School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farong","family":"Wen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Jia","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Ideagram 2.0","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5860\/choice.31-4736"},{"issue":"3","key":"ref3","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref4","article-title":"Methodology for the subjective assessment of the quality of television pictures","year":"2002","journal-title":"International Telecommunication Union"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102540"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref10","volume-title":"FLUX.1-dev","year":"2024"},{"key":"ref11","volume-title":"Fooocus","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.918441"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref14","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00128"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","author":"Ma","year":"2023","journal-title":"Dreamtalk: When expressive talking head generation meets diffusion probabilistic models"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF02944754"},{"key":"ref25","volume-title":"Midjourney","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4133-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"issue":"3","key":"ref28","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201ccompletely blind","volume":"20","author":"Mittal","year":"2012","journal-title":"image quality analyzer. IEEE Signal Processing Letters"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2502725"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131660"},{"key":"ref31","volume-title":"OpenDalleV1.1","year":"2023"},{"key":"ref32","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref34","volume-title":"ProteusV0.2","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299154"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917336"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130480"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01408"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00608"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2426416"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref50","author":"Zhang","year":"2024","journal-title":"Musetalk: Real-time high quality lip synchronization with latent space inpainting"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00423"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3570597"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00429"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095347"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222061"},{"key":"ref57","author":"Zhang","year":"2023","journal-title":"Simple baselines for projection-based fullreference and no-reference point cloud quality assessment"},{"key":"ref58","author":"Zhang","year":"2024","journal-title":"A-bench: Are 1 mms masters at evaluating ai-generated images"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3722559"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2023.3345656"},{"key":"ref61","volume-title":"Aibench: Towards trustworthy evaluation under the 45\u00b0 law","author":"Zhang","year":"2025"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3715134"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00938"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3081162"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171684"},{"key":"ref67","author":"Zhou","year":"2023","journal-title":"An implementation of multimodal fusion system for intelligent digital human generation"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310276"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10221964"},{"issue":"4","key":"ref70","article-title":"Perceptual quality assessment for point clouds: A survey","volume":"21","author":"Zhou","year":"2023","journal-title":"ZTE Communications"},{"key":"ref71","author":"Zhou","year":"2024","journal-title":"Memo-bench: A multiple benchmark for text-to-image and multimodal large language models on human emotion analysis"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647507"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680964"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889921"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849906"},{"key":"ref76","author":"Zhou","year":"2025","journal-title":"Q-agent: Quality-driven chain-of-thought image restoration agent through robust multimodal large language model"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-3729-7_2"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3572000"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2025.117371"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443462.pdf?arnumber=11443462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:25Z","timestamp":1777612465000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01134","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}