{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:15Z","timestamp":1750309515326,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":58,"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":"The Innovation Research Group Project of NSFC","award":["61921003"],"award-info":[{"award-number":["61921003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681172","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"2554-2563","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["\"Special Relativity\" of Image Aesthetics Assessment: a Preliminary Empirical Perspective"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1884-4920","authenticated-orcid":false,"given":"Rui","family":"Xie","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2952-7757","authenticated-orcid":false,"given":"Anlong","family":"Ming","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8817-0685","authenticated-orcid":false,"given":"Shuai","family":"He","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0679-6693","authenticated-orcid":false,"given":"Yi","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7199-5047","authenticated-orcid":false,"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. Metadata for Image Aesthetics Assessment with Aesthetic Attributes in Mobile Terminal Computational Photography Systems. ITU-T Recommendation. Approved on 2023-09--13."},{"key":"e_1_3_2_1_2_1","volume-title":"Automated aesthetic analysis of photographic images","author":"Aydin Tun\u00e7 Ozan","year":"2014","unstructured":"Tun\u00e7 Ozan Aydin, Aljoscha Smolic, and Markus Gross. 2014. Automated aesthetic analysis of photographic images. IEEE transactions on visualization and computer graphics 21, 1 (2014), 31--42."},{"key":"e_1_3_2_1_3_1","volume-title":"DXOMARK objective video quality measurements. Electronic Imaging","author":"Baudin Emilie","year":"2020","unstructured":"Emilie Baudin, Fran\u00e7ois-Xavier Bucher, Laurent Chanas, and Fr\u00e9d\u00e9ric Guichard. 2020. DXOMARK objective video quality measurements. Electronic Imaging (2020), 166--1."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102363"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115852"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191853"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Qiuyu Chen Wei Zhang Ning Zhou Peng Lei Yi Xu Yu Zheng and Jianping Fan. 2020. Adaptive fractional dilated convolution network for image aesthetics assessment. In CVPR. 14114--14123.","DOI":"10.1109\/CVPR42600.2020.01412"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744078_23"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995467"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Abhimanyu Dubey Nikhil Naik Devi Parikh Ramesh Raskar and C\u00e9sar A Hidalgo. 2016. Deep learning the city: Quantifying urban perception at a global scale. In ECCV. 196--212.","DOI":"10.1007\/978-3-319-46448-0_12"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Yuming Fang Hanwei Zhu Yan Zeng Kede Ma and ZhouWang. 2020. Perceptual quality assessment of smartphone photography. In CVPR. 3677--3686.","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"S Alireza Golestaneh Saba Dadsetan and Kris M Kitani. 2022. No-reference image quality assessment via transformers relative ranking and self-consistency. In WACV. 1220--1230.","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"e_1_3_2_1_14_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01996"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611881"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Shuai He Yongchang Zhang Rui Xie Dongxiang Jiang and Anlong Ming. 2022. Rethinking image aesthetics assessment: Models datasets and benchmarks. In IJCAI-22. 942--948.","DOI":"10.24963\/ijcai.2022\/132"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3389452"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225728"},{"key":"e_1_3_2_1_20_1","volume-title":"AesExpert: Towards Multimodality Foundation Model for Image Aesthetics Perception. arXiv preprint arXiv:2404.09624","author":"Huang Yipo","year":"2024","unstructured":"Yipo Huang, Xiangfei Sheng, Zhichao Yang, Quan Yuan, Zhichao Duan, Pengfei Chen, Leida Li, Weisi Lin, and Guangming Shi. 2024. AesExpert: Towards Multimodality Foundation Model for Image Aesthetics Perception. arXiv preprint arXiv:2404.09624 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"andWeisi Lin","author":"Huang Yipo","year":"2024","unstructured":"Yipo Huang, Quan Yuan, Xiangfei Sheng, Zhichao Yang, Haoning Wu, Pengfei Chen, Yuzhe Yang, Leida Li, andWeisi Lin. 2024. AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception. arXiv preprint arXiv:2401.08276 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Wei Jiang Alexander C Loui and Cathleen Daniels Cerosaletti. 2010. Automatic aesthetic value assessment in photographic images. In ICME. 920--925.","DOI":"10.1109\/ICME.2010.5582588"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3547144"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350970"},{"key":"e_1_3_2_1_25_1","volume-title":"Musiq: Multi-scale image quality transformer. In CVPR. 5148--5157.","author":"Ke Junjie","year":"2021","unstructured":"Junjie Ke, QifeiWang, YilinWang, Peyman Milanfar, and Feng Yang. 2021. Musiq: Multi-scale image quality transformer. In CVPR. 5148--5157."},{"key":"e_1_3_2_1_26_1","volume-title":"Vila: Learning image aesthetics from user comments with vision-language pretraining. In CVPR. 10041--10051.","author":"Ke Junjie","year":"2023","unstructured":"Junjie Ke, Keren Ye, Jiahui Yu, Yonghui Wu, Peyman Milanfar, and Feng Yang. 2023. Vila: Learning image aesthetics from user comments with vision-language pretraining. In CVPR. 10041--10051."},{"volume-title":"PAC-Net: Pairwise aesthetic comparison network for image aesthetic assessment","author":"Ko Keunsoo","key":"e_1_3_2_1_27_1","unstructured":"Keunsoo Ko, Jun-Tae Lee, and Chang-Su Kim. 2018. PAC-Net: Pairwise aesthetic comparison network for image aesthetic assessment. In ICIP. IEEE, 2491--2495."},{"volume-title":"Photo aesthetics ranking network with attributes and content adaptation","author":"Kong Shu","key":"e_1_3_2_1_28_1","unstructured":"Shu Kong, Xiaohui Shen, Zhe Lin, Radomir Mech, and Charless Fowlkes. 2016. Photo aesthetics ranking network with attributes and content adaptation. In ECCV. Springer, 662--679."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Jun-Tae Lee and Chang-Su Kim. 2019. Image aesthetic assessment based on pairwise comparison a unified approach to score regression binary classification and personalization. In CVPR. 1191--1200.","DOI":"10.1109\/ICCV.2019.00128"},{"key":"e_1_3_2_1_30_1","unstructured":"Seon-Ho Lee and Chang-Su Kim. 2020. Deep repulsive clustering of ordered data based on order-identity decomposition. In ICLR."},{"volume-title":"Order learning using partially ordered data via chainization","author":"Lee Seon-Ho","key":"e_1_3_2_1_31_1","unstructured":"Seon-Ho Lee and Chang-Su Kim. 2022. Order learning using partially ordered data via chainization. In ECCV. Springer, 196--211."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548244"},{"key":"e_1_3_2_1_35_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Liu Limin","year":"2024","unstructured":"Limin Liu, Shuai He, Anlong Ming, Rui Xie, and Huadong Ma. 2024. ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478557"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"volume-title":"Photo and video quality evaluation: Focusing on the subject","author":"Luo Yiwen","key":"e_1_3_2_1_38_1","unstructured":"Yiwen Luo and Xiaoou Tang. 2008. Photo and video quality evaluation: Focusing on the subject. In ECCV. Springer, 386--399."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3130752"},{"key":"e_1_3_2_1_40_1","volume-title":"A-lamp: Adaptive layout-aware multi-patch deep convolutional neural network for photo aesthetic assessment. In CVPR. 4535--4544.","author":"Ma Shuang","year":"2017","unstructured":"Shuang Ma, Jing Liu, and ChangWen Chen. 2017. A-lamp: Adaptive layout-aware multi-patch deep convolutional neural network for photo aesthetic assessment. In CVPR. 4535--4544."},{"key":"e_1_3_2_1_41_1","volume-title":"Learning photography aesthetics with deep cnns. arXiv preprint arXiv:1707.03981","author":"Malu Gautam","year":"2017","unstructured":"Gautam Malu, Raju S Bapi, and Bipin Indurkhya. 2017. Learning photography aesthetics with deep cnns. arXiv preprint arXiv:1707.03981 (2017)."},{"key":"e_1_3_2_1_42_1","volume-title":"AVA: A large-scale database for aesthetic visual analysis","author":"Murray Naila","year":"2012","unstructured":"Naila Murray, Luca Marchesotti, and Florent Perronnin. 2012. AVA: A large-scale database for aesthetic visual analysis. In CVPR. IEEE, 2408--2415."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.33134\/eeja.185"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611996"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Jan Pfister Konstantin Kobs and Andreas Hotho. 2021. Self-supervised multi-task pretraining improves image aesthetic assessment. In CVPR. 816--825.","DOI":"10.1109\/CVPRW53098.2021.00091"},{"key":"e_1_3_2_1_46_1","volume-title":"Research on Image Processing and Generative Teaching in the Context of AIGC. In 2022 3rd International Conference on Information Science and Education (ICISE-IE). IEEE, 20--25","author":"Rao Jian","year":"2022","unstructured":"Jian Rao, Chuqi Qiu, and Mengzhen Xiong. 2022. Research on Image Processing and Generative Teaching in the Context of AIGC. In 2022 3rd International Conference on Information Science and Education (ICISE-IE). IEEE, 20--25."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Jian Ren Xiaohui Shen Zhe Lin Radomir Mech and David J Foran. 2017. Personalized image aesthetics. In ICCV. 638--647.","DOI":"10.1109\/ICCV.2017.76"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Dongyu She Yu-Kun Lai Gaoxiong Yi and Kun Xu. 2021. Hierarchical layoutaware graph convolutional network for unified aesthetics assessment. In CVPR. 8475--8484.","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6026"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240554"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611969"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01820"},{"key":"e_1_3_2_1_53_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 27, 8 (2018), 3998--4011."},{"key":"e_1_3_2_1_54_1","volume-title":"Maxvit: Multi-axis vision transformer. In ECCV. 459--479.","author":"Tu Zhengzhong","year":"2022","unstructured":"Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, and Yinxiao Li. 2022. Maxvit: Multi-axis vision transformer. In ECCV. 459--479."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Faqiang Wang Wangmeng Zuo Liang Lin David Zhang and Lei Zhang. 2016. Joint learning of single-image and cross-image representations for person reidentification. In CVPR. 1288--1296.","DOI":"10.1109\/CVPR.2016.144"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Yuzhe Yang Liwu Xu Leida Li Nan Qie Yaqian Li Peng Zhang and Yandong Guo. 2022. Personalized image aesthetics assessment with rich attributes. In CVPR. 19861--19869.","DOI":"10.1109\/CVPR52688.2022.01924"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611942"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.02.008"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681172","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681172"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":58,"alternative-id":["10.1145\/3664647.3681172","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681172","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"}}]}}