{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:56:11Z","timestamp":1781538971958,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"the Shanxi Province Science and Technology Major Special Project","award":["202201150401021"],"award-info":[{"award-number":["202201150401021"]}]},{"name":"the Fundamental Research Program of Shanxi Province","award":["202303021212189, 202303021211153, 202203021212138, 202303021212206, 202303021212372, and 202403021212166"],"award-info":[{"award-number":["202303021212189, 202303021211153, 202203021212138, 202303021212206, 202303021212372, and 202403021212166"]}]},{"name":"the National Natural Science Foundation of China","award":["62272426"],"award-info":[{"award-number":["62272426"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810817","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"940-948","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Agglomerative Model Meets Multi-Scale Adaptive Fusion for Cross-Modal Unsupervised Domain Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2049-3089","authenticated-orcid":false,"given":"Zhixun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3276-5748","authenticated-orcid":false,"given":"Liqun","family":"Kuang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4463-8484","authenticated-orcid":false,"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2589-3533","authenticated-orcid":false,"given":"Shichao","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1198-8539","authenticated-orcid":false,"given":"Zhongyu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3596-6457","authenticated-orcid":false,"given":"Fengguang","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02071"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00015"},{"key":"e_1_3_3_1_6_2","first-page":"4340","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Gaidon Adrien","year":"2016","unstructured":"Adrien Gaidon, Qiao Wang, Yohann Cabon, and Eleonora Vig. 2016. Virtual worlds as proxy for multi-object tracking analysis. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4340\u20134349."},{"key":"e_1_3_3_1_7_2","unstructured":"Jakob Geyer Yohannes Kassahun Mentar Mahmudi Xavier Ricou Rupesh Durgesh Andrew\u00a0S Chung Lorenz Hauswald Viet\u00a0Hoang Pham Maximilian M\u00fchlegg Sebastian Dorn et\u00a0al. 2020. A2d2: Audi autonomous driving dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2004.06320 (2020)."},{"key":"e_1_3_3_1_8_2","unstructured":"He Guan Chunfeng Song and Zhaoxiang Zhang. 2025. LiDAR-camera Cooperative Semantic Segmentation. Machine Intelligence Research (2025) 1\u201313."},{"key":"e_1_3_3_1_9_2","first-page":"166","volume-title":"European Conference on Computer Vision","author":"Hao Xiaoshuai","year":"2024","unstructured":"Xiaoshuai Hao, Ruikai Li, Hui Zhang, Dingzhe Li, Rong Yin, Sangil Jung, Seung-In Park, ByungIn Yoo, Haimei Zhao, and Jing Zhang. 2024. Mapdistill: Boosting efficient camera-based hd map construction via camera-lidar fusion model distillation. In European Conference on Computer Vision. Springer, 166\u2013183."},{"key":"e_1_3_3_1_10_2","first-page":"22487","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Heinrich Greg","year":"2025","unstructured":"Greg Heinrich, Mike Ranzinger, Hongxu Yin, Yao Lu, Jan Kautz, Andrew Tao, Bryan Catanzaro, and Pavlo Molchanov. 2025. Radiov2. 5: Improved baselines for agglomerative vision foundation models. In Proceedings of the Computer Vision and Pattern Recognition Conference. 22487\u201322497."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01262"},{"key":"e_1_3_3_1_12_2","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems","author":"Li Fan","year":"2025","unstructured":"Fan Li, Xuan Wang, Xuanbin Wang, Zhaoxiang Zhang, and Yuelei Xu. 2025. No Object Is an Island: Enhancing 3D Semantic Segmentation Generalization with Diffusion Models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547990"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02004"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Ying Li Lingfei Ma Zilong Zhong Fei Liu Michael\u00a0A Chapman Dongpu Cao and Jonathan Li. 2020. Deep learning for lidar point clouds in autonomous driving: A review. IEEE Transactions on Neural Networks and Learning Systems 32 8 (2020) 3412\u20133432.","DOI":"10.1109\/TNNLS.2020.3015992"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00710"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00141"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Wei Liu Zhiming Luo Yuanzheng Cai Ying Yu Yang Ke Jos\u00e9\u00a0Marcato Junior Wesley\u00a0Nunes Gon\u00e7alves and Jonathan Li. 2021. Adversarial unsupervised domain adaptation for 3D semantic segmentation with multi-modal learning. ISPRS Journal of Photogrammetry and Remote Sensing 176 (2021) 211\u2013221.","DOI":"10.1016\/j.isprsjprs.2021.04.012"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00630"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00702"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Maomao Sun Ting Rui Jianqing Liu Dong Wang Chengsong Yang and Nan Zheng. 2025. Cross-modal unsupervised domain adaptation for 3D semantic segmentation via multi-scale fusion-then-distillation. Journal of King Saud University Computer and Information Sciences 37 7 (2025) 193.","DOI":"10.1007\/s44443-025-00201-4"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00576"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00262"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00908"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Jingyi Wang Yu Liu Hanlin Tan and Maojun Zhang. 2024. A survey on weakly supervised 3D point cloud semantic segmentation. IET Computer Vision 18 3 (2024) 329\u2013342.","DOI":"10.1049\/cvi2.12250"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Yao Wu Mingwei Xing Yachao Zhang Xiaotong Luo Yuan Xie and Yanyun Qu. 2024. Unidseg: Unified cross-domain 3d semantic segmentation via visual foundation models prior. Advances in Neural Information Processing Systems 37 (2024) 101223\u2013101249.","DOI":"10.52202\/079017-3210"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612013"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Yao Wu Mingwei Xing Yachao Zhang Yuan Xie Kaibei Peng and Yanyun Qu. 2025. Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation. IEEE Transactions on Circuits and Systems for Video Technology 35 9 (2025) 9030\u20139045.","DOI":"10.1109\/TCSVT.2025.3545971"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680582"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20183"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Aoran Xiao Xiaoqin Zhang Ling Shao and Shijian Lu. 2024. A survey of label-efficient deep learning for 3D point clouds. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 12 (2024) 9139\u20139160.","DOI":"10.1109\/TPAMI.2024.3416302"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Hanbiao Xiao Zhaozheng Hu Chen Lv Jie Meng Jianan Zhang and Ji\u2019an You. 2024. Progressive Multi-Modal Semantic Segmentation Guided SLAM Using Tightly-Coupled LiDAR-Visual-Inertial Odometry. IEEE Transactions on Intelligent Transportation Systems 26 2 (2024) 1645\u20131656.","DOI":"10.1109\/TITS.2024.3508695"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209459"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Jingyi Xu Weidong Yang Lingdong Kong Youquan Liu Qingyuan Zhou Rui Zhang Zhijun Li Wen-Ming Chen and Ben Fei. 2025. Visual foundation models boost cross-modal unsupervised domain adaptation for 3d semantic segmentation. IEEE Transactions on Intelligent Transportation Systems 26 11 (2025) 20287\u201320301.","DOI":"10.1109\/TITS.2025.3587430"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Mengyuan Yang Rui Yang Shikang Tao Xin Zhang and Min Wang. 2024. Unsupervised domain adaptive building semantic segmentation network by edge-enhanced contrastive learning. Neural Networks 179 (2024) 106581.","DOI":"10.1016\/j.neunet.2024.106581"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Xingyu Yuan Yu Liu Tifan Xiong Wei Zeng and Chao Wang. 2025. Semantic Fusion Algorithm of 2D LiDAR and Camera Based on Contour and Inverse Projection. Sensors 25 8 (2025) 2526.","DOI":"10.3390\/s25082526"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Yuxiao Zhang Alexander Carballo Hanting Yang and Kazuya Takeda. 2023. Perception and sensing for autonomous vehicles under adverse weather conditions: A survey. ISPRS Journal of Photogrammetry and Remote Sensing 196 (2023) 146\u2013177.","DOI":"10.1016\/j.isprsjprs.2022.12.021"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547987"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:29:04Z","timestamp":1781537344000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":37,"alternative-id":["10.1145\/3805622.3810817","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810817","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}