{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T21:52:21Z","timestamp":1772574741690,"version":"3.50.1"},"reference-count":46,"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":["62572458"],"award-info":[{"award-number":["62572458"]}],"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":["62406310"],"award-info":[{"award-number":["62406310"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0680202"],"award-info":[{"award-number":["XDB0680202"]}]},{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Planning Project","doi-asserted-by":"publisher","award":["Z251100008125009"],"award-info":[{"award-number":["Z251100008125009"]}],"id":[{"id":"10.13039\/501100012401","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science and Technology Council","award":["113-2221-E-006-161-MY3"],"award-info":[{"award-number":["113-2221-E-006-161-MY3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tvcg.2026.3658714","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:59:13Z","timestamp":1769633953000},"page":"2944-2961","source":"Crossref","is-referenced-by-count":0,"title":["Interactive Visual Assessment for Text-to-Image Generation Models"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0288-2444","authenticated-orcid":false,"given":"Xiaoyue","family":"Mi","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3975-2483","authenticated-orcid":false,"given":"Fan","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-1546","authenticated-orcid":false,"given":"Juan","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2481-5023","authenticated-orcid":false,"given":"Qiang","family":"Sheng","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3141-9979","authenticated-orcid":false,"given":"Ziyao","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3087-242X","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6699-2944","authenticated-orcid":false,"given":"Tong-Yee","family":"Lee","sequence":"additional","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"ref2","first-page":"7454","article-title":"Improving image generation with better captions","volume-title":"Comput. Sci.","author":"Betker","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104771"},{"key":"ref4","article-title":"X-IQE: Explainable image quality evaluation for text-to-image generation with visual large language models","author":"Chen","year":"2023"},{"key":"ref5","first-page":"54710","article-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-image generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Cho","year":"2024"},{"key":"ref6","first-page":"58648","article-title":"Stable diffusion is unstable","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Du","year":"2023"},{"key":"ref7","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref8","first-page":"295","article-title":"Domino: Discovering systematic errors with cross-modal embeddings","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eyuboglu","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3327168"},{"key":"ref10","article-title":"Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned","author":"Ganguli","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00370"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3352002"},{"key":"ref13","article-title":"Nano banana (Gemini 2.5 flash image) technical documentation","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3585077"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531907"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref19","first-page":"79889","article-title":"GenAI-Arena: An open evaluation platform for generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Jiang","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref21","first-page":"36652","article-title":"Pick-a-Pic: An open dataset of user preferences for text-to-image generation","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Kirstain","year":"2023"},{"key":"ref22","first-page":"69981","article-title":"Holistic evaluation of text-to-image models","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Lee","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3319020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","first-page":"56626","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Liu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.18"},{"key":"ref29","first-page":"56589","article-title":"Proving test set contamination for black-box language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Oren","year":"2024"},{"key":"ref30","first-page":"22275","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.230"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"ref36","article-title":"SimpleAR: Pushing the frontier of autoregressive visual generation through pretraining, SFT, and RL","author":"Wang","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"ref38","first-page":"1","article-title":"Discovering bugs in vision models using off-the-shelf image generation and captioning","volume-title":"Proc. NeurIPS ML Saf. Workshop","author":"Wiles","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00714"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3397712"},{"key":"ref42","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xu","year":"2023"},{"key":"ref43","first-page":"30084","article-title":"ReAct: Synergizing reasoning and acting in language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Yao","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/318774.318946"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3349050"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3466964"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11418562\/11367342.pdf?arnumber=11367342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:52:11Z","timestamp":1772571131000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11367342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":46,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3658714","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}