{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:00:10Z","timestamp":1783530010819,"version":"3.55.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991451"],"award-info":[{"award-number":["61991451"]}],"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":[[2025,2]]},"DOI":"10.1109\/tcsvt.2024.3470870","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:31:23Z","timestamp":1727717483000},"page":"1464-1477","source":"Crossref","is-referenced-by-count":11,"title":["Towards Explainable Image Aesthetics Assessment With Attribute-Oriented Critiques Generation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9069-8796","authenticated-orcid":false,"given":"Leida","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8468-1970","authenticated-orcid":false,"given":"Xiangfei","family":"Sheng","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7501-0009","authenticated-orcid":false,"given":"Jinjian","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9632-985X","authenticated-orcid":false,"given":"Weisheng","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3010181"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174817"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3303933"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2555658"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2189689"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2190924"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/11744078_23"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.303"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.84"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.60"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00960"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2968285"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611969"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967223"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2985526"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272984"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502083"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.119"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191853"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201510"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225728"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref32","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"issue":"8","key":"ref34","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350970"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25485"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3341611"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.380"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2019.0361"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3123468"},{"key":"ref43","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01412"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186307"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189276"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3313507"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941778"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2911428"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/132"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611881"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3365174"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3423268.3423590"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01924"},{"key":"ref59","article-title":"Learning photography aesthetics with deep CNNs","author":"Malu","year":"2017","journal-title":"arXiv:1707.03981"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093412"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859845"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref65","article-title":"Otter: A multi-modal model with in-context instruction tuning","author":"Li","year":"2023","journal-title":"arXiv:2305.03726"},{"key":"ref66","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2310.03744"},{"key":"ref67","article-title":"mPLUG-Owl2: Revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2023","journal-title":"arXiv:2311.04257"},{"key":"ref68","article-title":"AesBench: An expert benchmark for multimodal large language models on image aesthetics perception","author":"Huang","year":"2024","journal-title":"arXiv:2401.08276"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3290479"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10885778\/10700814.pdf?arnumber=10700814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:47:04Z","timestamp":1740084424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10700814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":72,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3470870","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}