{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T05:08:22Z","timestamp":1781068102136,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176224, 62176092, 62222602, 62306165"],"award-info":[{"award-number":["62176224, 62176092, 62222602, 62306165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology on Sonar Laboratory","award":["2024-JCJQ-LB-32\/07"],"award-info":[{"award-number":["2024-JCJQ-LB-32\/07"]}]},{"DOI":"10.13039\/501100015282","name":"China Academy of Railway Sciences","doi-asserted-by":"publisher","award":["2023Y1357"],"award-info":[{"award-number":["2023Y1357"]}],"id":[{"id":"10.13039\/501100015282","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755793","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"2226-2234","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["PLATO-TTA: Prototype-Guided Pseudo-Labeling and Adaptive Tuning for Multi-Modal Test-Time Adaptation of 3D Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1566-3344","authenticated-orcid":false,"given":"Jianxiang","family":"Xie","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0227-5641","authenticated-orcid":false,"given":"Yao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6153-5004","authenticated-orcid":false,"given":"Yachao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6064-5818","authenticated-orcid":false,"given":"Xiaopei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of California, Los Angeles, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-7437","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8926-4162","authenticated-orcid":false,"given":"Yanyun","family":"Qu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_3_1","volume-title":"European Conference on Computer Vision. Springer, 232-249","author":"Cao Haozhi","year":"2024","unstructured":"Haozhi Cao, Yuecong Xu, Jianfei Yang, Pengyu Yin, Xingyu Ji, Shenghai Yuan, and Lihua Xie. 2024. Reliable spatial-temporal voxels for multi-modal test-time adaptation. In European Conference on Computer Vision. Springer, 232-249."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01724"},{"key":"e_1_3_2_1_5_1","volume-title":"Maximilian M\u00fchlegg, Sebastian Dorn, Tiffany Fernandez, Martin J\u00e4nicke, Sudesh Mirashi, Chiragkumar Savani, Martin Sturm, Oleksandr Vorobiov, Martin Oelker, Sebastian Garreis, and Peter Schuberth.","author":"Geyer Jakob","year":"2020","unstructured":"Jakob Geyer, Yohannes Kassahun, Mentar Mahmudi, Xavier Ricou, Rupesh Durgesh, Andrew S. Chung, Lorenz Hauswald, Viet Hoang Pham, Maximilian M\u00fchlegg, Sebastian Dorn, Tiffany Fernandez, Martin J\u00e4nicke, Sudesh Mirashi, Chiragkumar Savani, Martin Sturm, Oleksandr Vorobiov, Martin Oelker, Sebastian Garreis, and Peter Schuberth. 2020. A2D2: Audi Autonomous Driving Dataset. arXiv:2004.06320 [cs.CV] https:\/\/arxiv.org\/abs\/2004.06320"},{"key":"e_1_3_2_1_6_1","first-page":"6204","article-title":"Test time adaptation via conjugate pseudo-labels","volume":"35","author":"Goyal Sachin","year":"2022","unstructured":"Sachin Goyal, Mingjie Sun, Aditi Raghunathan, and J Zico Kolter. 2022. Test time adaptation via conjugate pseudo-labels. Advances in Neural Information Processing Systems, Vol. 35 (2022), 6204-6218.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. pmlr, 448-456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. pmlr, 448-456."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159589"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547990"},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 6028-6039","author":"Liang Jian","year":"2020","unstructured":"Jian Liang, Dapeng Hu, and Jiashi Feng. 2020. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International conference on machine learning. PMLR, 6028-6039."},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 16888-16905","author":"Niu Shuaicheng","year":"2022","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, and Mingkui Tan. 2022. Efficient test-time model adaptation without forgetting. In International conference on machine learning. PMLR, 16888-16905."},{"key":"e_1_3_2_1_12_1","volume-title":"Towards stable test-time adaptation in dynamic wild world. arXiv preprint arXiv:2302.12400","author":"Niu Shuaicheng","year":"2023","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Zhiquan Wen, Yaofo Chen, Peilin Zhao, and Mingkui Tan. 2023. Towards stable test-time adaptation in dynamic wild world. arXiv preprint arXiv:2302.12400 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00702"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Ros German","unstructured":"German Ros, Laura Sellart, Joanna Materzynska, David Vazquez, and Antonio M. Lopez. 2016. The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_16_1","first-page":"16928","article-title":"Mm-tta: multi-modal test-time adaptation for 3d semantic segmentation","author":"Shin Inkyu","year":"2022","unstructured":"Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang, Samuel Schulter, Buyu Liu, Sparsh Garg, In So Kweon, and Kuk-Jin Yoon. 2022. Mm-tta: multi-modal test-time adaptation for 3d semantic segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16928-16937.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 1239-1249","author":"Simons Cody","unstructured":"Cody Simons, Dripta S. Raychaudhuri, Sk Miraj Ahmed, Suya You, Konstantinos Karydis, and Amit K. Roy-Chowdhury. 2023. SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 1239-1249."},{"key":"e_1_3_2_1_18_1","volume-title":"Revisiting realistic test-time training: Sequential inference and adaptation by anchored clustering regularized self-training","author":"Su Yongyi","year":"2024","unstructured":"Yongyi Su, Xun Xu, Tianrui Li, and Kui Jia. 2024. Revisiting realistic test-time training: Sequential inference and adaptation by anchored clustering regularized self-training. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"e_1_3_2_1_20_1","volume-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems","author":"Tarvainen Antti","year":"2017","unstructured":"Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_21_1","volume-title":"Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726","author":"Wang Dequan","year":"2020","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2020. Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"Towards understanding gd with hard and conjugate pseudo-labels for test-time adaptation. arXiv preprint arXiv:2210.10019","author":"Wang Jun-Kun","year":"2022","unstructured":"Jun-Kun Wang and Andre Wibisono. 2022. Towards understanding gd with hard and conjugate pseudo-labels for test-time adaptation. arXiv preprint arXiv:2210.10019 (2022)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612013"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680582"},{"key":"e_1_3_2_1_25_1","volume-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems, Vol. 34 (2021), 12077-12090."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25400"},{"key":"e_1_3_2_1_27_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Yang Mouxing","year":"2024","unstructured":"Mouxing Yang, Yunfan Li, Changqing Zhang, Peng Hu, and Xi Peng. 2024. Test-time adaptation against multi-modal reliability bias. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01528"},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 41753-41769","author":"Zhang Qingyang","year":"2023","unstructured":"Qingyang Zhang, Haitao Wu, Changqing Zhang, Qinghua Hu, Huazhu Fu, Joey Tianyi Zhou, and Xi Peng. 2023. Provable dynamic fusion for low-quality multimodal data. In International conference on machine learning. PMLR, 41753-41769."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547987"},{"key":"e_1_3_2_1_31_1","unstructured":"Yufei Zhang Yicheng Xu Hongxin Wei Zhiping Lin and Huiping Zhuang. 2024. Analytic Continual Test-Time Adaptation for Multi-Modality Corruption. arXiv:2410.22373 [cs.LG] https:\/\/arxiv.org\/abs\/2410.22373"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:39:58Z","timestamp":1765309198000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":31,"alternative-id":["10.1145\/3746027.3755793","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755793","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}