{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T15:01:45Z","timestamp":1780066905819,"version":"3.54.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62471349"],"award-info":[{"award-number":["62471349"]}],"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":["62171340"],"award-info":[{"award-number":["62171340"]}],"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":["62301378"],"award-info":[{"award-number":["62301378"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["QTZX25076"],"award-info":[{"award-number":["QTZX25076"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M762553"],"award-info":[{"award-number":["2024M762553"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Fund of Xidian University","award":["YJSJ24012"],"award-info":[{"award-number":["YJSJ24012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3632637","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:50:18Z","timestamp":1763146218000},"page":"958-971","source":"Crossref","is-referenced-by-count":1,"title":["AesPrompt: Zero-Shot Image Aesthetics Assessment With Multi-Granularity Aesthetic Prompt Learning"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8468-1970","authenticated-orcid":false,"given":"Xiangfei","family":"Sheng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9069-8796","authenticated-orcid":false,"given":"Leida","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0509-3782","authenticated-orcid":false,"given":"Pengfei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Chongqing Three Gorges University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5840-5743","authenticated-orcid":false,"given":"Giuseppe","family":"Valenzise","sequence":"additional","affiliation":[{"name":"CNRS, CentraleSupelec, Laboratoire des Signaux et Systèmes, Université Paris Saclay, Gif-sur-Yvette, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2962548"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3237969"},{"key":"ref4","first-page":"36652","article-title":"Pick-a-Pic: An open dataset of user preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kirstain","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521765"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611881"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611969"},{"key":"ref10","article-title":"Q-Mamba: On first exploration of vision mamba for image quality assessment","author":"Guan","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117709"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2018.2828326"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548244"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3290479"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189276"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447301"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680649"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref21","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1037\/aca0000716"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-81465-6_6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11744078_23"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.303"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2010.5654231"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126498"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.119"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.84"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.60"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108921"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2968285"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3470870"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967223"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2985526"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201510"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272984"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref43","article-title":"AesBench: An expert benchmark for multimodal large language models on image aesthetics perception","author":"Huang","year":"2024"},{"key":"ref44","article-title":"UNIAA: A unified multi-modal image aesthetic assessment baseline and benchmark","author":"Zhou","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref48","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref49","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref50","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"ref53","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350970"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/132"},{"key":"ref58","first-page":"7672","article-title":"Paintings and drawings aesthetics assessment with rich attributes for various artistic categories","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Jin","year":"2024"},{"key":"ref59","article-title":"Simulacra aesthetic captions","author":"Pressman","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941778"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3123468"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02144"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11249440.pdf?arnumber=11249440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:05Z","timestamp":1768255325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3632637","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}