{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:12:22Z","timestamp":1782400342852,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Funds for Creative Research Groups of China","award":["under Grant 61921003"],"award-info":[{"award-number":["under Grant 61921003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611881","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"1023-1032","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["EAT: An Enhancer for Aesthetics-Oriented Transformers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8817-0685","authenticated-orcid":false,"given":"Shuai","family":"He","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5717-5851","authenticated-orcid":false,"given":"Shuntian","family":"Zheng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7514-3709","authenticated-orcid":false,"given":"Haobin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"166","article-title":"DXOMARK Objective Video Quality Measurements","volume":"2020","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, 9 (2020), 166--1.","journal-title":"Electronic Imaging"},{"key":"e_1_3_2_1_2_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_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475467"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_1_5_1","volume-title":"Studying aesthetics in photographic images using a computational approach","author":"Datta Ritendra","unstructured":"Ritendra Datta, Dhiraj Joshi, Jia Li, and James Z Wang. 2006. Studying aesthetics in photographic images using a computational approach. In ECCV. Springer, 288--301."},{"key":"e_1_3_2_1_6_1","volume-title":"Imagenet: A large-scale hierarchical image database. In CVPR. Ieee, 248--255.","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In CVPR. Ieee, 248--255."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2696576"},{"key":"e_1_3_2_1_8_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_9_1","unstructured":"Jacob Gildenblat and contributors. 2021. PyTorch library for CAM methods. https:\/\/github.com\/jacobgil\/pytorch-grad-cam."},{"key":"e_1_3_2_1_10_1","volume-title":"Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks. IJCAI","author":"He Shuai","year":"2022","unstructured":"Shuai He, Yongchang Zhang, Rui Xie, Dongxiang Jiang, and Anlong Ming. 2022. Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks. IJCAI (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Vlad Hosu Bastian Goldlucke and Dietmar Saupe. 2019. Effective aesthetics prediction with multi-level spatially pooled features. In CVPR.","DOI":"10.1109\/CVPR.2019.00960"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186307"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189276"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/35058500"},{"key":"e_1_3_2_1_15_1","volume-title":"MUSIQ: Multi-scale Image Quality Transformer. In ICCV. 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 ICCV. 5148--5157."},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_17_1","volume-title":"Photo aesthetics ranking network with attributes and content adaptation","author":"Kong Shu","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_18_1","unstructured":"Bonan Li Yinhan Hu Xuecheng Nie Congying Han Xiangjian Jiang Tiande Guo and Luoqi Liu. 2023. DropKey. In CVPR."},{"key":"e_1_3_2_1_19_1","first-page":"3898","article-title":"Personality-assisted multi-task learning for generic and personalized image aesthetics assessment","volume":"29","author":"Li Leida","year":"2020","unstructured":"Leida Li, Hancheng Zhu, Sicheng Zhao, Guiguang Ding, and Weisi Lin. 2020. Personality-assisted multi-task learning for generic and personalized image aesthetics assessment. IEEE TIP 29 (2020), 3898--3910.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548244"},{"key":"e_1_3_2_1_21_1","volume-title":"Swin transformer: Hierarchical vision transformer using shifted windows. arXiv:2103.14030","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv:2103.14030 (2021)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478557"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_29"},{"key":"e_1_3_2_1_24_1","volume-title":"User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learning. arXiv:2106.07488","author":"Lv Pei","year":"2021","unstructured":"Pei Lv, Jianqi Fan, Xixi Nie, Weiming Dong, Xiaoheng Jiang, Bing Zhou, Mingliang Xu, and Changsheng Xu. 2021. User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learning. arXiv:2106.07488 (2021)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240635"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Shuang Ma Jing Liu and Chang Wen Chen. 2017. A-Lamp: Adaptive Layout- Aware Multi-patch Deep Convolutional Neural Network for Photo Aesthetic Assessment. In CVPR. 722--731.","DOI":"10.1109\/CVPR.2017.84"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Long Mai Hailin Jin and Feng Liu. 2016. Composition-Preserving Deep Photo Aesthetics Assessment. In CVPR. 497--506.","DOI":"10.1109\/CVPR.2016.60"},{"key":"e_1_3_2_1_28_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."},{"key":"e_1_3_2_1_29_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_30_1","doi-asserted-by":"crossref","unstructured":"Dongyu She Yu-Kun Lai Gaoxiong Yi and Kun Xu. 2021. Hierarchical Layout- Aware Graph Convolutional Network for Unified Aesthetics Assessment. In CVPR. 8475--8484.","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Kekai Sheng Weiming Dong Chongyang Ma Xing Mei Feiyue Huang and Bao-Gang Hu. 2018. Attention-based multi-patch aggregation for image aesthetic assessment. In ACMMM.","DOI":"10.1145\/3240508.3240554"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.40"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2688929"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"e_1_3_2_1_35_1","volume-title":"MaxViT: Multi-Axis Vision Transformer. ECCV","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. ECCV (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 568--578","author":"Xie Enze","year":"2021","unstructured":"WenhaiWang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. 2021. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 568--578."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"e_1_3_2_1_39_1","volume-title":"Personalized image aesthetics assessment via meta-learning with bilevel gradient optimization. TCYB","author":"Zhu Hancheng","year":"2020","unstructured":"Hancheng Zhu, Leida Li, Jinjian Wu, Sicheng Zhao, Guiguang Ding, and Guangming Shi. 2020. Personalized image aesthetics assessment via meta-learning with bilevel gradient optimization. TCYB (2020)."},{"key":"e_1_3_2_1_40_1","volume-title":"Learning personalized image aesthetics from subjective and objective attributes","author":"Zhu Hancheng","year":"2021","unstructured":"Hancheng Zhu, Yong Zhou, Leida Li, Yaqian Li, and Yandong Guo. 2021. Learning personalized image aesthetics from subjective and objective attributes. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"e_1_3_2_1_42_1","volume-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations.","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611881","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:42Z","timestamp":1755820842000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":42,"alternative-id":["10.1145\/3581783.3611881","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611881","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}