{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:34:35Z","timestamp":1774539275446,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFC3305002"],"award-info":[{"award-number":["2023YFC3305002"]}]},{"name":"Research Foundation of Education Bureau of Hunan Province","award":["23A0462"],"award-info":[{"award-number":["23A0462"]}]},{"name":"Major Project of Xiangjiang Laboratory","award":["23XJ01003,23XJ01007"],"award-info":[{"award-number":["23XJ01003,23XJ01007"]}]},{"name":"Natural Science Foundation of Hunan Province","award":["2024JJ5113"],"award-info":[{"award-number":["2024JJ5113"]}]},{"name":"NSFC","award":["62202161"],"award-info":[{"award-number":["62202161"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681511","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"10008-10017","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Align-IQA: Aligning Image Quality Assessment Models with Diverse Human Preferences via Customizable Guidance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7771-0260","authenticated-orcid":false,"given":"Junfeng","family":"Yang","sequence":"first","affiliation":[{"name":"Hunan University of Technology and Business & Xiangjiang Laboratory, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7976-1468","authenticated-orcid":false,"given":"Jing","family":"Fu","sequence":"additional","affiliation":[{"name":"Hunan University of Technology and Business & Xiangjiang Laboratory, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2974-5781","authenticated-orcid":false,"given":"Zhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hunan University of Technology and Business & Xiangjiang Laboratory, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0105-074X","authenticated-orcid":false,"given":"Limei","family":"Liu","sequence":"additional","affiliation":[{"name":"Hunan University of Technology and Business & Xiangjiang Laboratory, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4944-0547","authenticated-orcid":false,"given":"Qin","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University of Technology and Business & Xiangjiang Laboratory, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6850-4027","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7462-2783","authenticated-orcid":false,"given":"Wenzhi","family":"Cao","sequence":"additional","affiliation":[{"name":"Hunan University of Technology and Business & Xiangjiang Laboratory, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-017-1166-8"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760518"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 1597--1607. https:\/\/proceedings.mlr.press\/v119\/chen20j.html"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_5_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arxiv","author":"Dosovitskiy Alexey","year":"2010","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arxiv: 2010.11929 [cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2639328"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00123"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.3267105"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3245991"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35728-2_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774045"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181496"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_2_1_24_1","volume-title":"Blind image quality assessment: From natural scene statistics to perceptual quality","author":"Moorthy Anush Krishna","year":"2011","unstructured":"Anush Krishna Moorthy and Alan Conrad Bovik. 2011. Blind image quality assessment: From natural scene statistics to perceptual quality. IEEE transactions on Image Processing, Vol. 20, 12 (2011), 3350--3364."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2440172"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Nikolay Ponomarenko Lina Jin Oleg Ieremeiev Vladimir Lukin Karen Egiazarian Jaakko Astola Benoit Vozel Kacem Chehdi Marco Carli Federica Battisti et al. 2015. Image database TID2013: Peculiarities results and perspectives. Signal processing: Image communication Vol. 30 (2015) 57--77.","DOI":"10.1016\/j.image.2014.10.009"},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_28_1","volume-title":"The statistics of natural images. Network: computation in neural systems","author":"Ruderman Daniel L","year":"1994","unstructured":"Daniel L Ruderman. 1994. The statistics of natural images. Network: computation in neural systems, Vol. 5, 4 (1994), 517."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00566"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_1_32_1","volume-title":"NIMA: Neural image assessment","author":"Talebi Hossein","year":"2018","unstructured":"Hossein Talebi and Peyman Milanfar. 2018. NIMA: Neural image assessment. IEEE transactions on image processing, Vol. 27, 8 (2018), 3998--4011."},{"key":"e_1_3_2_1_33_1","volume-title":"Computational versus psychophysical bottom-up image saliency: A comparative evaluation study","author":"Toet Alexander","year":"2011","unstructured":"Alexander Toet. 2011. Computational versus psychophysical bottom-up image saliency: A comparative evaluation study. IEEE transactions on pattern analysis and machine intelligence, Vol. 33, 11 (2011), 2131--2146."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2945675"},{"key":"e_1_3_2_1_35_1","unstructured":"Haoning Wu Zicheng Zhang Weixia Zhang Chaofeng Chen Liang Liao Chunyi Li Yixuan Gao Annan Wang Erli Zhang Wenxiu Sun Qiong Yan Xiongkuo Min Guangtao Zhai and Weisi Lin. 2023. Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels. arxiv: 2312.17090 [cs.CV] https:\/\/arxiv.org\/abs\/2312.17090"},{"key":"e_1_3_2_1_36_1","volume-title":"Levine (Eds.)","volume":"36","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 15903--15935. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/33646ef0ed554145eab65f6250fab0c9-Paper-Conference.pdf"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2585880"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904879"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00641"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"e_1_3_2_1_41_1","volume-title":"2012 IEEE conference on computer vision and pattern recognition. IEEE, 1098--1105","author":"Ye Peng","year":"2012","unstructured":"Peng Ye, Jayant Kumar, Le Kang, and David Doermann. 2012. Unsupervised feature learning framework for no-reference image quality assessment. In 2012 IEEE conference on computer vision and pattern recognition. IEEE, 1098--1105."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"e_1_3_2_1_43_1","volume-title":"PSCR: Patches Sampling-based Contrastive Regression for AIGC Image Quality Assessment. arxiv: 2312.05897 [cs.CV] https:\/\/arxiv.org\/abs\/2312.05897","author":"Yuan Jiquan","year":"2023","unstructured":"Jiquan Yuan, Xinyan Cao, Linjing Cao, Jinlong Lin, and Xixin Cao. 2023. PSCR: Patches Sampling-based Contrastive Regression for AIGC Image Quality Assessment. arxiv: 2312.05897 [cs.CV] https:\/\/arxiv.org\/abs\/2312.05897"},{"key":"e_1_3_2_1_44_1","volume-title":"TIER: Text-Image Encoder-based Regression for AIGC Image Quality Assessment. arxiv: 2401.03854 [cs.CV] https:\/\/arxiv.org\/abs\/2401.03854","author":"Yuan Jiquan","year":"2024","unstructured":"Jiquan Yuan, Xinyan Cao, Jinming Che, Qinyuan Wang, Sen Liang, Wei Ren, Jinlong Lin, and Xixin Cao. 2024. TIER: Text-Image Encoder-based Regression for AIGC Image Quality Assessment. arxiv: 2401.03854 [cs.CV] https:\/\/arxiv.org\/abs\/2401.03854"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 22302--22313","author":"Zhao Kai","year":"2023","unstructured":"Kai Zhao, Kun Yuan, Ming Sun, Mading Li, and Xing Wen. 2023. Quality-Aware Pre-Trained Models for Blind Image Quality Assessment. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 22302--22313."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902484"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681511","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681511"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":49,"alternative-id":["10.1145\/3664647.3681511","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681511","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}