{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T03:39:02Z","timestamp":1780544342927,"version":"3.54.1"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"11","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2024,11,30]]},"abstract":"<jats:p>\n            Image Aesthetic Assessment (IAA) is an emerging paradigm that predicts aesthetic score as the popular aesthetic taste for an image. Previous IAA approaches take a single image as input to predict the aesthetic score of the image. However, we discover that most existing IAA methods fail dramatically to predict the images with a large variance of aesthetic voting distribution. Motivated by the practice that people consider similar experiences to improve the consistence of the voting result, we present a novel Multiple Image joint Learning Network (MILNet) to mimic this natural process. Our novelty is mainly three-fold: (a) Semantic-based retrieval method that constructs aesthetic similarity (the similarity of aesthetic attribution) to select reference images; (b) Graph network reasoning that initializes and updates the weight of intrinsic relationships among multiple images; (c) Adaptive Earth Mover\u2019s Distance (AdaEMD) loss function that adjusts weight for easy and hard instances to mitigate unbalanced distribution of aesthetic datasets. Our evaluation with the benchmark AVA and TAD datasets demonstrates that the proposed MILNet outperforms state-of-the-art IAA methods. The code is available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/flyingbird93\/MILNet\">https:\/\/github.com\/flyingbird93\/MILNet<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3687128","type":"journal-article","created":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T23:57:30Z","timestamp":1724284650000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Improving Image Aesthetic Assessment via Multiple Image Joint Learning"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4260-3905","authenticated-orcid":false,"given":"Tengfei","family":"Shi","sequence":"first","affiliation":[{"name":"School of Computer Engineering, Hubei University of Arts and Science, Xiangyang, China and State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9982-5667","authenticated-orcid":false,"given":"Chenglizhao","family":"Chen","sequence":"additional","affiliation":[{"name":"Qingdao Institute of Software College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7990-500X","authenticated-orcid":false,"given":"Zhenyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5774-6706","authenticated-orcid":false,"given":"Aimin","family":"Hao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-3586","authenticated-orcid":false,"given":"Yuming","family":"Fang","sequence":"additional","affiliation":[{"name":"Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01412"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490033"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3414843"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995467"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564607"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.920744"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.486"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611881"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/132"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00960"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413695"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3288760"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00658"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3328993"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651399"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451621"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00958"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2968285"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548244"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_1"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093412"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.118"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102078"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.119"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3130752"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.84"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.60"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126444"},{"key":"e_1_3_2_37_2","unstructured":"Naila Murray and Albert Gordo. 2017. A deep architecture for unified aesthetic prediction. arXiv:1708.04890. Retrieved from https:\/\/arxiv.org\/pdf\/1708.04890"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_16"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3328991"},{"key":"e_1_3_2_41_2","first-page":"8026","volume-title":"Proceedings of the 33rd International Conference onNeural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. Pytorch: An imperative style, high-performance deep learning library. In Proceedings of the 33rd International Conference onNeural Information Processing Systems, 8026\u20138037."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1049\/cp:20070055"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.76"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240554"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01127"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745362"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2710419"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413834"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3169017"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02144"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111303"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941778"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3024207"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2984670"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3687128","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3687128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:21Z","timestamp":1750295421000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3687128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":60,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11,30]]}},"alternative-id":["10.1145\/3687128"],"URL":"https:\/\/doi.org\/10.1145\/3687128","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"2023-06-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}