{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:04:14Z","timestamp":1782403454157,"version":"3.54.5"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301316"],"award-info":[{"award-number":["62301316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571324"],"award-info":[{"award-number":["62571324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3639620","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:44:30Z","timestamp":1764787470000},"page":"4636-4649","source":"Crossref","is-referenced-by-count":6,"title":["AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-1748","authenticated-orcid":false,"given":"Yunhao","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7753-1596","authenticated-orcid":false,"given":"Sijing","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8162-1949","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1466-6383","authenticated-orcid":false,"given":"Zhichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3069-060X","authenticated-orcid":false,"given":"Yucheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"USC-SJTU Institute of Cultural and Creative Industry, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref2","article-title":"Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image generation","author":"Li","year":"2024","journal-title":"arXiv:2402.17245"},{"key":"ref3","volume-title":"Midjourney","author":"Holz et al","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612831"},{"key":"ref5","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv:2306.09341"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_5"},{"key":"ref10","article-title":"Internvl2: Better than the best\u2014Expanding performance boundaries of open-source multimodal models with the progressive scaling strategy","author":"Team","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref12","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref13","article-title":"InternLM2 technical report","volume-title":"arXiv:2403.17297","author":"Cai","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00664"},{"key":"ref15","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301276"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00283"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3350049"},{"key":"ref19","article-title":"F-bench: Rethinking human preference evaluation metrics for benchmarking face generation, customization, and restoration","author":"Liu","year":"2024","journal-title":"arXiv:2412.13155"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00961"},{"key":"ref21","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv:1809.11096"},{"key":"ref22","article-title":"A style-based generator architecture for generative adversarial networks","author":"Karras","year":"2018","journal-title":"arXiv:1812.04948"},{"key":"ref23","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref25","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arXiv:2404.02905"},{"key":"ref26","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref27","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref28","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv:2011.13456"},{"key":"ref29","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv:2406.06525"},{"key":"ref30","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530104"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755700"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2025.104321"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374887"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231041"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3504854"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32795"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00644"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681471"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00641"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2014.10.009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758304"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755332"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3380260"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2011.6190099"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2018.8698654"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3486336"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205770"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2024.3447454"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3278452"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref62","article-title":"Q-align: Teaching LMMs for visual scoring via discrete text-defined levels","author":"Wu","year":"2023","journal-title":"arXiv:2312.17090"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3571788"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3434999"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc9050132"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1186\/s42492-024-00171-w"},{"key":"ref68","volume-title":"DeepFloyd IF: A Novel State-of-the-Art Open-Source Text-to-Image Model With a High Degree of Photorealism and Language Understanding","author":"At StabilityAI","year":"2023"},{"key":"ref69","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref70","volume-title":"Dreamlike.art","year":"2023"},{"key":"ref71","article-title":"PixArt-$\\alpha$\n: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv:2310.00426"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref73","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref75","volume-title":"Methodology for the Subjective Assessment of the Quality of Television Pictures","year":"2012"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref77","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref78","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref79","article-title":"Dual-branch network for portrait image quality assessment","author":"Sun","year":"2024","journal-title":"arXiv:2405.08555"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00257"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3420083"},{"key":"ref84","article-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv:2403.05525"},{"key":"ref85","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024","journal-title":"arXiv:2412.05271"},{"key":"ref86","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref87","volume-title":"LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge","author":"Liu","year":"2024"},{"key":"ref88","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref89","article-title":"No-reference quality assessment of contrast-distorted images using contrast enhancement","author":"Yan","year":"2019","journal-title":"arXiv:1904.08879"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131660"},{"key":"ref91","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00134"},{"key":"ref93","article-title":"Demystifying MMD GANs","author":"Bi\u0144kowski","year":"2018","journal-title":"arXiv:1801.01401"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2355716"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713945"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11275847.pdf?arnumber=11275847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:03:03Z","timestamp":1775592183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11275847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":97,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3639620","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}