{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:46:28Z","timestamp":1771613188976,"version":"3.50.1"},"reference-count":71,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"name":"Open Project Program of the State Key Laboratory of CAD&CG","award":["A2416"],"award-info":[{"award-number":["A2416"]}]},{"name":"Guangzhou Philosophy Social Science Project","award":["2024GZGJ17"],"award-info":[{"award-number":["2024GZGJ17"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2022ZYGXZR020"],"award-info":[{"award-number":["2022ZYGXZR020"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Guangzhou Basic Research Program Basic and Applied Basic Research Special General Project","award":["SL2024A04J00955"],"award-info":[{"award-number":["SL2024A04J00955"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>Style is prone to experience but hard to formulate, even for design professionals. The current style classification (SC) methods can be categorized into mono-tasking (style) and multi-tasking (style, artists, genre, and other additional clues). However, the style strength spread-out phenomenon challenges them by the uncertain noises\u2019 distribution and unstable distinguishable feature representation. The multiple sub-styles make the principal style recognition hard for current SC approaches with lower accuracy. This article proposes the community transferrable representation learning (CTRL) framework inspired by community detection and style transfer studies. The community feature is the transferrable feature embeddings in latent space through all samples within the same style concept. Therefore, instead of learning the unique style features, we introduce the learnable transferrable embeddings, whose distance will be smaller for the intraclass and larger for the interclass, to represent the principal style concept. There are two generative processes, p-AE and q-AE, as the cooperative operations to learn the community styles by the proposed diamond cells (D-cells) in a stacked way. The proposed community loss includes two terms: the invariance term is used to make the principal style embedding consistent, and the redundancy reduction term can decorate the different vector embeddings of sub-styles. The style classification and style feature learning model are optimized simultaneously in a semi-supervised way to learn the class-level style representation. We conduct experiments on six style datasets (three oil paintings, one architecture, one fashion, and one general image). Results show that the proposed framework brings a performance gain of 2%\u20137% in terms of accuracy compared with the SOTA approaches.<\/jats:p>","DOI":"10.1145\/3735136","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T10:52:02Z","timestamp":1747047122000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Community Transferrable Representation Learning for Image Style Classification"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1631-0535","authenticated-orcid":false,"given":"Jia","family":"Cui","sequence":"first","affiliation":[{"name":"School of Design, South China University of Technology, Guangzhou, China and State Key Laboratory of Subtropical Building and Urban Science, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4789-9585","authenticated-orcid":false,"given":"Jinchen","family":"Shen","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1821-2288","authenticated-orcid":false,"given":"Jialin","family":"Wei","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2581-385X","authenticated-orcid":false,"given":"Shiyu","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2633-3300","authenticated-orcid":false,"given":"Zhaojia","family":"Ye","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7420-1791","authenticated-orcid":false,"given":"Shijian","family":"Luo","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7248-8329","authenticated-orcid":false,"given":"Zhen","family":"Qin","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,12]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127811"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127434"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126231"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127202"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.08.013"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107903"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.2671523"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-022-02208-0"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967251"},{"key":"e_1_3_2_11_2","unstructured":"K. Ghosal M. Prasad and A. Smolic. 2019. A geometry-sensitive approach for photographic style classification. arXiv:1909.01040. Retrieved from https:\/\/arxiv.org\/abs\/1909.01040"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771766"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02178-3"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.076"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21061940"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09995-z"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475586"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376730"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1080\/07294360.2021.1937066"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2023.3245729"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126654"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.38094\/jastt20165"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/buildings13092280"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127105"},{"key":"e_1_3_2_25_2","volume-title":"Computer Vision-ECCV 2014 Workshops","author":"Bar Y.","year":"2014","unstructured":"Y. Bar, N. Levy, and L. Wolf. 2014. Classification of artistic styles using binarized features derived from a deep neural network. In Computer Vision-ECCV 2014 Workshops. Springer."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766929"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-023-10172-1"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104121"},{"issue":"12","key":"e_1_3_2_29_2","first-page":"1848","article-title":"Supervised heterogeneous sparse feature selection for Chinese paintings classification","volume":"25","author":"Wang Z.","year":"2013","unstructured":"Z. Wang, M. Sun, Y. Han, and D. Zhang. 2013. Supervised heterogeneous sparse feature selection for Chinese paintings classification. Journal of Computer-Aided Design and Computer Graphics 25, 12 (2013), 1848\u20131855.","journal-title":"Journal of Computer-Aided Design and Computer Graphics"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the 9th International Conference on Digital Image Processing (ICDIP \u201917)","author":"Souleyman C.","year":"2017","unstructured":"C. Souleyman, H. Yao, Y. Gu, and M. Amrani. 2017. Deep feature extraction and combination for remote sensing image classification based on pre-trained CNN models. In Proceedings of the 9th International Conference on Digital Image Processing (ICDIP \u201917). SPIE."},{"key":"e_1_3_2_34_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Simonyan K.","year":"2015","unstructured":"K. Simonyan and A. Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458885"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109776"},{"key":"e_1_3_2_40_2","unstructured":"R. S. R. Silva A. Lotfi I. K. Ihianle G. Shahtahmassebi J. J. Bird. 2024. ArtBrain: An explainable end-to-end toolkit for classification and attribution of AI-generated art and style. arXiv:2412.01512. Retrieved from https:\/\/arxiv.org\/abs\/2412.01512"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2023.101899"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02348-z"},{"key":"e_1_3_2_43_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Hong Z.","year":"2024","unstructured":"Z. Hong, Z. Wang, L. Shen, Y. Yao, Z. Huang, S. Chen, C. Yang, M. Gong, and T. Liu. 2024. Improving non-transferable representation learning by harnessing content and style. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_2_44_2","unstructured":"G. Strezoski and M. Worring. 2017. Omniart: Multi-task deep learning for artistic data analysis. arXiv:1708.00684. Retrieved from https:\/\/arxiv.org\/abs\/1708.00684"},{"issue":"5","key":"e_1_3_2_45_2","first-page":"970","article-title":"Robust text detection in natural scene images","volume":"36","author":"Yin X.-C.","year":"2013","unstructured":"X.-C. Yin, X. Yin, K. Huang, H.-W. Hao. 2013. Robust text detection in natural scene images. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 5 (2013), 970\u2013983.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.05.036"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3657624"},{"key":"e_1_3_2_48_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford A.","year":"2021","unstructured":"A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, et al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning. PMLR."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging10070156"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE62371.2024.10761042"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2946695"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2012.08.002"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207645"},{"key":"e_1_3_2_54_2","doi-asserted-by":"crossref","unstructured":"M. Vijendran F. W. Li and H. P. Shum. 2023. Tackling data bias in painting classification with style transfer. arXiv:2301.02524. Retrieved from https:\/\/arxiv.org\/abs\/2301.02524","DOI":"10.5220\/0011776600003417"},{"key":"e_1_3_2_55_2","unstructured":"C. Li and B. Harrison. 2022. StyleM: Stylized metrics for image captioning built with contrastive n-grams. arXiv:2201.00975. Retrieved from https:\/\/arxiv.org\/abs\/2201.00975"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-014-0621-6"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760382"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.263"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_39"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_2_64_2","unstructured":"B. Wu C. Xu X. Dai A. Wan P. Zhang Z. Yan M. Tomizuka J. Gonzalez K. Keutzer and P. Vajda. 2020. Visual transformers: Token-based image representation and processing for computer vision. arXiv:2006.03677. Retrieved from https:\/\/arxiv.org\/abs\/2006.03677"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.3390\/app121910062"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06527-9_28"},{"issue":"12","key":"e_1_3_2_67_2","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent P.","year":"2010","unstructured":"P. Vincent, H. Larochelle, I. Lajoie, Y. Q. Bengio, and P. A. Manzagol. 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 11 (2010), 12.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.243"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05683-9"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-023-09420-1"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00504"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281507"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3735136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T10:16:11Z","timestamp":1752747371000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3735136"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":71,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3735136"],"URL":"https:\/\/doi.org\/10.1145\/3735136","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2024-09-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}