{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T19:49:25Z","timestamp":1782589765277,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":54,"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":"National Natural Science Foundation of China","award":["62171340, 61991451, 61771473"],"award-info":[{"award-number":["62171340, 61991451, 61771473"]}]},{"DOI":"10.13039\/501100001809","name":"OPPO Research Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611969","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"1117-1126","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["AesCLIP: Multi-Attribute Contrastive Learning for Image Aesthetics Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8468-1970","authenticated-orcid":false,"given":"Xiangfei","family":"Sheng","sequence":"first","affiliation":[{"name":"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":"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":"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":"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":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9098-2105","authenticated-orcid":false,"given":"Yuzhe","family":"Yang","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7651-5081","authenticated-orcid":false,"given":"Liwu","family":"Xu","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3582-9997","authenticated-orcid":false,"given":"Yaqian","family":"Li","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2179-3292","authenticated-orcid":false,"given":"Guangming","family":"Shi","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. \"O'Reilly Media","author":"Bird Steven","unstructured":"Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. \"O'Reilly Media, Inc.\"."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191853"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. IEEE, 3534--3543","author":"Chang Kuang-Yu","year":"2017","unstructured":"Kuang-Yu Chang, Kung-Hung Lu, and Chu-Song Chen. 2017. Aesthetic Critiques Generation for Photos. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, 3534--3543."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2696576"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995467"},{"key":"e_1_3_2_1_7_1","volume-title":"CLIP-Adapter: Better Vision-Language Models With Feature Adapters. arXiv preprint arXiv:2110.04544","author":"Gao Peng","year":"2021","unstructured":"Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yongfeng Zhang, Hongsheng Li, and Yu Qiao. 2021. CLIP-Adapter: Better Vision-Language Models With Feature Adapters. arXiv preprint arXiv:2110.04544 (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/132"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00960"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-021-01124-6"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of International Conference on Machine Learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning with Noisy Text Supervision. In Proceedings of International Conference on Machine Learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350970"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2011.941851"},{"key":"e_1_3_2_1_14_1","volume-title":"EVA: An Explainable Visual Aesthetics Dataset. In Joint Workshop on Aesthetic and Technical Quality Assessment of Multimedia and Media Analytics for Societal Trends. 5--13","author":"Kang Chen","year":"2020","unstructured":"Chen Kang, Giuseppe Valenzise, and Fr\u00e9d\u00e9ric Dufaux. 2020. EVA: An Explainable Visual Aesthetics Dataset. In Joint Workshop on Aesthetic and Technical Quality Assessment of Multimedia and Media Analytics for Societal Trends. 5--13."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","volume":"1","author":"Ke Yan","year":"2006","unstructured":"Yan Ke, Xiaoou Tang, and Feng Jing. 2006. The Design of High-Level Features for Photo Quality Assessment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1. IEEE, 419--426."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744078_23"},{"key":"e_1_3_2_1_19_1","unstructured":"Junnan Li Ramprasaath Selvaraju Akhilesh Gotmare Shafiq Joty Caiming Xiong and Steven Chu Hong Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In Advances in Neural Information Processing Systems. 9694--9705."},{"key":"e_1_3_2_1_20_1","volume-title":"Psychology Inspired Model for Hierarchical Image Aesthetic Attribute Prediction. In 2022 IEEE International Conference on Multimedia and Expo. IEEE, 1--6.","author":"Li Leida","year":"2022","unstructured":"Leida Li, Jiachen Duan, Yuzhe Yang, Liwu Xu, Yaqian Li, and Yandong Guo. 2022. Psychology Inspired Model for Hierarchical Image Aesthetic Attribute Prediction. In 2022 IEEE International Conference on Multimedia and Expo. IEEE, 1--6."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2968285"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093412"},{"key":"e_1_3_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc., 13--23."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.119"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. IEEE, 2206--2213","author":"Luo Wei","year":"2011","unstructured":"Wei Luo, Xiaogang Wang, and Xiaoou Tang. 2011. Content-based Photo Quality Assessment. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, 2206--2213."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01752"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.84"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.60"},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126444"},{"key":"e_1_3_2_1_34_1","volume-title":"A Deep Architecture for Unified Aesthetic Prediction. arXiv preprint arXiv:1708.04890","author":"Murray Naila","year":"2017","unstructured":"Naila Murray and Albert Gordo. 2017. A Deep Architecture for Unified Aesthetic Prediction. arXiv preprint arXiv:1708.04890 (2017)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354807"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995539"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201510"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of 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 Proceedings of International conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"e_1_3_2_1_41_1","volume-title":"Vl-Bert: Pre-training of Generic Visual-Linguistic Representations. arXiv preprint arXiv:1908.08530","author":"Su Weijie","year":"2019","unstructured":"Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2019. Vl-Bert: Pre-training of Generic Visual-Linguistic Representations. arXiv preprint arXiv:1908.08530 (2019)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"e_1_3_2_1_43_1","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Nieto Daniel Vera","year":"2022","unstructured":"Daniel Vera Nieto, Luigi Celona, and Clara Fernandez Labrador. 2022. Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment. In Advances in Neural Information Processing Systems, Vol. 35. Curran Associates, Inc., 34148--34161."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840724"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01924"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941778"},{"key":"e_1_3_2_1_48_1","volume-title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling. arXiv preprint arXiv:2111.03930","author":"Zhang Renrui","year":"2021","unstructured":"Renrui Zhang, Rongyao Fang, Wei Zhang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Qiao, and Hongsheng Li. 2021. Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling. arXiv preprint arXiv:2111.03930 (2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2985526"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967223"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3123468"}],"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\/3581783.3611969","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:11:20Z","timestamp":1755821480000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611969"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":54,"alternative-id":["10.1145\/3581783.3611969","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611969","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"}}]}}