{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T20:10:52Z","timestamp":1793477452620,"version":"4.5.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shanghai Pujiang Program","award":["22PJ1406800"],"award-info":[{"award-number":["22PJ1406800"]}]},{"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\/501100002858","name":"China Post-Doctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","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":[[2024,8]]},"DOI":"10.1109\/tcsvt.2023.3319020","type":"journal-article","created":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T14:40:20Z","timestamp":1695652820000},"page":"6833-6846","source":"Crossref","is-referenced-by-count":201,"title":["AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0634-1710","authenticated-orcid":false,"given":"Chunyi","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\/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\/0000-0001-8642-8101","authenticated-orcid":false,"given":"Haoning","family":"Wu","sequence":"additional","affiliation":[{"name":"S-Laboratory, Nanyang Technological University, Cluny Road, Singapore"}],"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\/0000-0001-5693-0416","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\/0000-0001-6377-4730","authenticated-orcid":false,"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"John Hopcroft Center, 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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"S-Laboratory, Nanyang Technological University, Cluny Road, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.07.019"},{"key":"ref2","article-title":"Text-to-image diffusion models in generative AI: A survey","author":"Zhang","year":"2023","journal-title":"arXiv:2303.07909"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185316"},{"key":"ref4","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref7","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ding"},{"key":"ref8","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref9","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref10","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref12","article-title":"Text-guided synthesis of artistic images with retrieval-augmented diffusion models","volume-title":"arXiv:2207.13038","author":"Rombach","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"ref14","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2023","journal-title":"arXiv:2304.05977"},{"key":"ref15","article-title":"DiffusionDB: A large-scale prompt gallery dataset for text-to-image generative models","author":"Wang","year":"2022","journal-title":"arXiv:2210.14896"},{"key":"ref16","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","author":"Kirstain","year":"2023","journal-title":"arXiv:2305.01569"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref18","first-page":"1","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref19","first-page":"1","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":"ref20","article-title":"Demystifying MMD GANs","author":"Binkowski","year":"2018","journal-title":"arXiv:1801.01401"},{"key":"ref21","article-title":"Learning to evaluate the artness of AI-generated images","author":"Chen","year":"2023","journal-title":"arXiv:2305.04923"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00286"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611923"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00152"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2023.3270621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3470970"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2461891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949270"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref31","article-title":"X-IQE: Explainable image quality evaluation for text-to-image generation with visual large language models","author":"Chen","year":"2023","journal-title":"arXiv:2305.10843"},{"key":"ref32","first-page":"1","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language alignment","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Xue"},{"key":"ref33","article-title":"A pathway towards responsible AI generated content","author":"Chen","year":"2023","journal-title":"arXiv:2303.01325"},{"key":"ref34","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref35","volume-title":"Midjourney","author":"Holz","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref37","article-title":"Generated faces in the wild: Quantitative comparison of stable diffusion, midjourney and DALL-E2","author":"Borji","year":"2022","journal-title":"arXiv:2210.00586"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3425780"},{"key":"ref40","volume-title":"Methodology for the Subjective Assessment of the Quality of Television Pictures","year":"2002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186714"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886277"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2014.2344471"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229839"},{"key":"ref47","article-title":"Seeing is not always believing: Benchmarking human and model perception of AI-generated images","author":"Lu","year":"2023","journal-title":"arXiv:2304.13023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00284"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3265842"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2202676"},{"key":"ref51","first-page":"129","article-title":"Models of word segmentation in fluent maternal speech to infants","volume-title":"Signal to Syntax","author":"Aslin"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"ref53","article-title":"No-reference quality assessment of contrast-distorted images using contrast enhancement","author":"Yan","year":"2019","journal-title":"arXiv:1904.08879"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/QOMEX.2009.5246972"},{"issue":"3","key":"ref55","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a","volume":"20","author":"Mittal","year":"2012","journal-title":"IEEE Signal Process. Lett."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2355716"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713945"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref69","article-title":"TOPIQ: A top-down approach from semantics to distortions for image quality assessment","author":"Chen","year":"2023","journal-title":"arXiv:2308.03060"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10262331.pdf?arnumber=10262331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T01:50:49Z","timestamp":1723513849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10262331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":70,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3319020","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}