{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:14:23Z","timestamp":1765008863209,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201560, 62171294, 62371305"],"award-info":[{"award-number":["62201560, 62171294, 62371305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2025A1515010141 and 2024A1515030025"],"award-info":[{"award-number":["2025A1515010141 and 2024A1515030025"]}]},{"name":"Shenzhen Fundamental Research Program","award":["JCYJ20240813155034044"],"award-info":[{"award-number":["JCYJ20240813155034044"]}]},{"name":"Stable Support Project of Shenzhen","award":["20231128010046001"],"award-info":[{"award-number":["20231128010046001"]}]},{"name":"Key project of Shenzhen Science and Technology Plan","award":["20220810180617001"],"award-info":[{"award-number":["20220810180617001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770979","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:11Z","timestamp":1765008491000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Content-enhanced Tokens for Domain Generalized Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7616-8382","authenticated-orcid":false,"given":"Shishun","family":"Tian","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1506-7214","authenticated-orcid":false,"given":"Ziqi","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1389-9089","authenticated-orcid":false,"given":"Wenbin","family":"Zou","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5702-1927","authenticated-orcid":false,"given":"Yuanhao","family":"Gong","sequence":"additional","affiliation":[{"name":"Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6761-8767","authenticated-orcid":false,"given":"Guanghui","family":"Yue","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2624-5332","authenticated-orcid":false,"given":"Ting","family":"Su","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Shenzhen MSU-BIT University, Shenzhen, China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27840"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01767"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Liang-Chieh Chen George Papandreou Iasonas Kokkinos Kevin Murphy and Alan\u00a0L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets atrous convolution and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40 4 (2017) 834\u2013848.","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_3_1_9_2","unstructured":"Bowen Cheng Alex Schwing and Alexander Kirillov. 2021. Per-pixel classification is not all you need for semantic segmentation. Advances in neural information processing systems 34 (2021) 17864\u201317875."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01141"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Dinu Coltuc Philippe Bolon and J-M Chassery. 2006. Exact histogram specification. IEEE Transactions on Image processing 15 5 (2006) 1143\u20131152.","DOI":"10.1109\/TIP.2005.864170"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01479"},{"key":"e_1_3_3_1_14_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01751"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Jintao Guo Lei Qi Yinghuan Shi and Yang Gao. 2023. PLACE dropout: A progressive layer-wise and channel-wise dropout for domain generalization. ACM Transactions on Multimedia Computing Communications and Applications 20 3 (2023) 1\u201323.","DOI":"10.1145\/3624015"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Ernest\u00a0L Hall. 2006. Almost uniform distributions for computer image enhancement. IEEE Trans. Comput. 100 2 (2006) 207\u2013208.","DOI":"10.1109\/T-C.1974.223892"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","first-page":"II\u2013II","DOI":"10.1109\/CVPR.2004.1315232","volume-title":"Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.","volume":"2","author":"He Xuming","year":"2004","unstructured":"Xuming He, Richard\u00a0S Zemel, and Miguel\u00a0A Carreira-Perpin\u00e1n. 2004. Multiscale conditional random fields for image labeling. In Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. , Vol.\u00a02. IEEE, II\u2013II."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00299"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00970"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_3_1_28_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.05101 (2017)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00281"},{"key":"e_1_3_3_1_31_2","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et\u00a0al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.07193 (2023)."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00262"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Duo Peng Yinjie Lei Lingqiao Liu Pingping Zhang and Jun Liu. 2021. Global and local texture randomization for synthetic-to-real semantic segmentation. IEEE Transactions on Image Processing 30 (2021) 6594\u20136608.","DOI":"10.1109\/TIP.2021.3096334"},{"key":"e_1_3_3_1_35_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_1_38_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1409.1556 (2014)."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Jingdong Wang Ke Sun Tianheng Cheng Borui Jiang Chaorui Deng Yang Zhao Dong Liu Yadong Mu Mingkui Tan Xinggang Wang et\u00a0al. 2020. Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence 43 10 (2020) 3349\u20133364.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"e_1_3_3_1_41_2","unstructured":"Enze Xie Wenhai Wang Zhiding Yu Anima Anandkumar Jose\u00a0M Alvarez and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems 34 (2021) 12077\u201312090."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20193"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680906"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383008"},{"key":"e_1_3_3_1_45_2","unstructured":"Fisher Yu Wenqi Xian Yingying Chen Fangchen Liu Mike Liao Vashisht Madhavan Trevor Darrell et\u00a0al. 2018. Bdd100k: A diverse driving video database with scalable annotation tooling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1805.04687 2 5 (2018) 6."},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00219"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00787"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_31"},{"key":"e_1_3_3_1_50_2","unstructured":"Zhun Zhong Yuyang Zhao Gim\u00a0Hee Lee and Nicu Sebe. 2022. Adversarial style augmentation for domain generalized urban-scene segmentation. Advances in neural information processing systems 35 (2022) 338\u2013350."}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:10:30Z","timestamp":1765008630000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770979"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":49,"alternative-id":["10.1145\/3743093.3770979","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770979","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}