{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:29:53Z","timestamp":1778257793487,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"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 Fundamental Research Funds for the Central Universities","award":["3282023014"],"award-info":[{"award-number":["3282023014"]}]},{"name":"the Key Program of Beijing Polytechnic College","award":["BGY2023KY-16Z"],"award-info":[{"award-number":["BGY2023KY-16Z"]}]},{"name":"the Natural Science Foundation of China","award":["62072014"],"award-info":[{"award-number":["62072014"]}]},{"name":"Innovation Fund for Chinese Universities-Beichuang Teaching Assistant Project (Phase II)","award":["2021BCE01010"],"award-info":[{"award-number":["2021BCE01010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3688867.3690176","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T18:28:27Z","timestamp":1729708107000},"page":"11-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Text-guided Multi-Task Image Aesthetic Quality Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4029-0255","authenticated-orcid":false,"given":"Hongtao","family":"Yang","sequence":"first","affiliation":[{"name":"Communication University of China & Beijing Polytechnic College, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4874-2639","authenticated-orcid":false,"given":"Guolong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of International Business and Economics, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0393-0751","authenticated-orcid":false,"given":"Yehui","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Polytechnic College, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7744-6246","authenticated-orcid":false,"given":"Ping","family":"Shi","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1340-4402","authenticated-orcid":false,"given":"Xinghui","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3873-1653","authenticated-orcid":false,"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing Electronic Science and Technology of Institute, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 794--803","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning. PMLR, 794--803."},{"key":"e_1_3_2_1_2_1","volume-title":"Domain adaptation via prompt learning","author":"Ge Chunjiang","year":"2023","unstructured":"Chunjiang Ge, Rui Huang, Mixue Xie, Zihang Lai, Shiji Song, Shuang Li, and Gao Huang. 2023. Domain adaptation via prompt learning. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_3_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. 942--948.","DOI":"10.24963\/ijcai.2022\/132"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.976235"},{"key":"e_1_3_2_1_5_1","volume-title":"2017 IEEE International Conference on Image Processing (ICIP). IEEE, 1722--1726","author":"Kairanbay Magzhan","year":"2017","unstructured":"Yong-Lian Hii, John See, Magzhan Kairanbay, and Lai-Kuan Wong. 2017. Multigap: Multi-pooled inception network with text augmentation for aesthetic prediction of photographs. In 2017 IEEE International Conference on Image Processing (ICIP). IEEE, 1722--1726."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00960"},{"key":"e_1_3_2_1_7_1","volume-title":"ILGNet: Inception modules with connected local and global features for efficient image aesthetic quality classification using domain adaptation. IET computer vision","author":"Jin Xin","year":"2019","unstructured":"Xin Jin, Le Wu, Xiaodong Li, Xiaokun Zhang, Jingying Chi, Siwei Peng, Shiming Ge, Geng Zhao, and Shuying Li. 2019. ILGNet: Inception modules with connected local and global features for efficient image aesthetic quality classification using domain adaptation. IET computer vision, Vol. 13, 2 (2019), 206--212."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651399"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings, Part I 14","author":"Kong Shu","year":"2016","unstructured":"Shu Kong, Xiaohui Shen, Zhe Lin, Radomir Mech, and Charless Fowlkes. 2016. Photo aesthetics ranking network with attributes and content adaptation. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part I 14. Springer, 662--679."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859845"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2968285"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093412"},{"key":"e_1_3_2_1_18_1","volume-title":"Auto-lambda: Disentangling dynamic task relationships. arXiv preprint arXiv:2202.03091","author":"Liu Shikun","year":"2022","unstructured":"Shikun Liu, Stephen James, Andrew J Davison, and Edward Johns. 2022. Auto-lambda: Disentangling dynamic task relationships. arXiv preprint arXiv:2202.03091 (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240635"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.84"},{"key":"e_1_3_2_1_23_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_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354807"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201510"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301679"},{"key":"e_1_3_2_1_28_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_29_1","volume-title":"Multi-task learning as multi-objective optimization. Advances in neural information processing systems","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"Scaling","author":"Thurstone Louis L","unstructured":"Louis L Thurstone. 2017. A law of comparative judgment. In Scaling. Routledge, 81--92."},{"key":"e_1_3_2_1_33_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530068"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00741"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941778"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2985526"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967223"}],"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 2nd International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688867.3690176","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3688867.3690176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:34:25Z","timestamp":1755974065000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688867.3690176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":40,"alternative-id":["10.1145\/3688867.3690176","10.1145\/3688867"],"URL":"https:\/\/doi.org\/10.1145\/3688867.3690176","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"}}]}}