{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T18:01:25Z","timestamp":1785693685119,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100015282","name":"China Academy of Railway Sciences","doi-asserted-by":"publisher","award":["No.2023YJ357"],"award-info":[{"award-number":["No.2023YJ357"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100015282","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Computer Federation (CCF)-Lenovo Blue Ocean Research Fund"},{"name":"CAAI-Huawei MindSpore Open Fund"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100005230","name":"Natural Science Foundation of Chongqing","doi-asserted-by":"publisher","award":["No.CSTB2023NSCQJQX0007"],"award-info":[{"award-number":["No.CSTB2023NSCQJQX0007"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62176224, No.62176092, No.62222602, No.62306165"],"award-info":[{"award-number":["No.62176224, No.62176092, No.62222602, No.62306165"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["No.2023M731957"],"award-info":[{"award-number":["No.2023M731957"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680582","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"8662-8671","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["CLIP2UDA: Making Frozen CLIP Reward Unsupervised Domain Adaptation in 3D Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0227-5641","authenticated-orcid":false,"given":"Yao","family":"Wu","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2728-4096","authenticated-orcid":false,"given":"Mingwei","family":"Xing","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, 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":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-7437","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"East China Normal University & Chongqing Institute of 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, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jens Behley Martin Garbade Andres Milioto Jan Quenzel Sven Behnke Cyrill Stachniss and Jurgen Gall. 2019. SemanticKITTI: A dataset for semantic scene understanding of lidar sequences. In ICCV. 9297--9307.","DOI":"10.1109\/ICCV.2019.00939"},{"key":"e_1_3_2_1_2_1","volume-title":"Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, and Oscar Beijbom.","author":"Caesar Holger","year":"2020","unstructured":"Holger Caesar, Varun Bankiti, Alex H Lang, Sourabh Vora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, and Oscar Beijbom. 2020. nuScenes: A multimodal dataset for autonomous driving. In CVPR. 11621--11631."},{"key":"e_1_3_2_1_3_1","unstructured":"Haozhi Cao Yuecong Xu Jianfei Yang Pengyu Yin Shenghai Yuan and Lihua Xie. 2023. MoPA: Multi-modal prior aided domain adaptation for 3d semantic segmentation. arXiv preprint arXiv:2309.11839 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00015"},{"key":"e_1_3_2_1_5_1","unstructured":"Runnan Chen Youquan Liu Lingdong Kong Nenglun Chen Xinge Zhu Yuexin Ma Tongliang Liu and Wenping Wang. 2023. Towards label-free scene understanding by vision foundation models. In NeurIPS. 75896--75910."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Runnan Chen Youquan Liu Lingdong Kong Xinge Zhu Yuexin Ma Yikang Li Yuenan Hou Yu Qiao and Wenping Wang. 2023. CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP. In CVPR. 7020--7030.","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"e_1_3_2_1_7_1","volume-title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding. In CVPR. 7010--7019.","author":"Ding Runyu","year":"2023","unstructured":"Runyu Ding, Jihan Yang, Chuhui Xue, Wenqing Zhang, Song Bai, and Xiaojuan Qi. 2023. PLA: Language-Driven Open-Vocabulary 3D Scene Understanding. In CVPR. 7010--7019."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Adrien Gaidon Qiao Wang Yohann Cabon and Eleonora Vig. 2016. Virtual worlds as proxy for multi-object tracking analysis. In CVPR. 4340--4349.","DOI":"10.1109\/CVPR.2016.470"},{"key":"e_1_3_2_1_9_1","volume-title":"Maximilian M\u00fchlegg, Sebastian Dorn, et al.","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, et al. 2020. A2D2: Audi autonomous driving dataset. arXiv preprint arXiv:2004.06320 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Benjamin Graham Martin Engelcke and Laurens Van Der Maaten. 2018. 3d semantic segmentation with submanifold sparse convolutional networks. In CVPR. 9224--9232.","DOI":"10.1109\/CVPR.2018.00961"},{"key":"e_1_3_2_1_11_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_12_1","volume-title":"Wanli Ouyang, and Wangmeng Zuo.","author":"Huang Tianyu","year":"2023","unstructured":"Tianyu Huang, Bowen Dong, Yunhan Yang, Xiaoshui Huang, Rynson WH Lau, Wanli Ouyang, and Wangmeng Zuo. 2023. CLIP2Point: Transfer clip to point cloud classification with image-depth pre-training. In ICCV. 22157--22167."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Maximilian Jaritz Tuan-Hung Vu Raoul de Charette Emilie Wirbel and Patrick P\u00e9rez. 2020. xMUDA: Cross-modal unsupervised domain adaptation for 3d semantic segmentation. In CVPR. 12605--12614.","DOI":"10.1109\/CVPR42600.2020.01262"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Muhammad Uzair Khattak Hanoona Rasheed Muhammad Maaz Salman Khan and Fahad Shahbaz Khan. 2023. MaPLe: Multi-modal prompt learning. In CVPR. 19113--19122.","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. In ICCV. 4015--4026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Lingdong Kong Niamul Quader and Venice Erin Liong. 2023. ConDA: Unsupervised domain adaptation for lidar segmentation via regularized domain concatenation. In ICRA. 9338--9345.","DOI":"10.1109\/ICRA48891.2023.10160410"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Hyeongjun Kwon Taeyong Song Somi Jeong Jin Kim Jinhyun Jang and Kwanghoon Sohn. 2023. Probabilistic Prompt Learning for Dense Prediction. In CVPR. 6768--6777.","DOI":"10.1109\/CVPR52729.2023.00654"},{"key":"e_1_3_2_1_18_1","volume-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICML. 12888--12900.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICML. 12888--12900."},{"key":"e_1_3_2_1_19_1","volume-title":"Lidarcap: Long-range marker-less 3d human motion capture with lidar point clouds. In CVPR. 20502--20512.","author":"Li Jialian","year":"2022","unstructured":"Jialian Li, Jingyi Zhang, Zhiyong Wang, Siqi Shen, Chenglu Wen, Yuexin Ma, Lan Xu, Jingyi Yu, and Cheng Wang. 2022. Lidarcap: Long-range marker-less 3d human motion capture with lidar point clouds. In CVPR. 20502--20512."},{"key":"e_1_3_2_1_20_1","unstructured":"Miaoyu Li Yachao Zhang Yuan Xie Zuodong Gao Cuihua Li Zhizhong Zhang and Yanyun Qu. 2022. Cross-Domain and Cross-Modal Knowledge Distillation in Domain Adaptation for 3D Semantic Segmentation. In ACM MM. 3829--3837."},{"key":"e_1_3_2_1_21_1","unstructured":"Yunsheng Li Lu Yuan and Nuno Vasconcelos. 2019. Bidirectional learning for domain adaptation of semantic segmentation. In CVPR. 6936--6945."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Yuqi Lin Minghao Chen Wenxiao Wang Boxi Wu Ke Li Binbin Lin Haifeng Liu and Xiaofei He. 2023. Clip is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation. In CVPR. 15305--15314.","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"e_1_3_2_1_23_1","volume-title":"Wesley Nunes Gonccalves, and Jonathan Li.","author":"Liu Wei","year":"2021","unstructured":"Wei Liu, Zhiming Luo, Yuanzheng Cai, Ying Yu, Yang Ke, Jos\u00e9 Marcato Junior, Wesley Nunes Gonccalves, and Jonathan Li. 2021. Adversarial unsupervised domain adaptation for 3D semantic segmentation with multi-modal learning. ISPRS (2021), 211--221."},{"key":"e_1_3_2_1_24_1","unstructured":"Huaishao Luo Junwei Bao Youzheng Wu Xiaodong He and Tianrui Li. 2023. SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation. In ICML. 23033--23044."},{"key":"e_1_3_2_1_25_1","unstructured":"Pietro Morerio Jacopo Cavazza and Vittorio Murino. 2018. Minimal-entropy correlation alignment for unsupervised deep domain adaptation. In ICLR. 1--14."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Duo Peng Yinjie Lei Wen Li Pingping Zhang and Yulan Guo. 2021. Sparse-to-dense feature matching: Intra and inter domain cross-modal learning in domain adaptation for 3d semantic segmentation. In ICCV. 7108--7117.","DOI":"10.1109\/ICCV48922.2021.00702"},{"key":"e_1_3_2_1_27_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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, et al. 2021. Learning transferable visual models from natural language supervision. In ICML. 8748--8763."},{"key":"e_1_3_2_1_28_1","unstructured":"Yongming Rao Wenliang Zhao Guangyi Chen Yansong Tang Zheng Zhu Guan Huang Jie Zhou and Jiwen Lu. 2022. DenseCLIP: Language-guided dense prediction with context-aware prompting. In CVPR. 18082--18091."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Olaf Ronneberger Philipp Fischer and Thomas Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In MICCAI. 234--241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. ImageNet large scale visual recognition challenge. IJCV (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Cristiano Saltori Fabio Galasso Giuseppe Fiameni Nicu Sebe Elisa Ricci and Fabio Poiesi. 2022. CosMix: Compositional semantic mix for domain adaptation in 3d lidar segmentation. In ECCV. 586--602.","DOI":"10.1007\/978-3-031-19827-4_34"},{"key":"e_1_3_2_1_32_1","volume-title":"Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909","author":"Sennrich Rico","year":"2015","unstructured":"Rico Sennrich, Barry Haddow, and Alexandra Birch. 2015. Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)."},{"key":"e_1_3_2_1_33_1","volume-title":"Carlo Ratti, and Daniela Rus","author":"Shan Tixiao","year":"2020","unstructured":"Tixiao Shan, Brendan Englot, Drew Meyers, Wei Wang, Carlo Ratti, and Daniela Rus. 2020. Lio-sam: Tightly-coupled lidar inertial odometry via smoothing and mapping. In IROS. 5135--5142."},{"key":"e_1_3_2_1_34_1","volume-title":"Alpha-CLIP: A clip model focusing on wherever you want. arXiv preprint arXiv:2312.03818","author":"Sun Zeyi","year":"2023","unstructured":"Zeyi Sun, Ye Fang, Tong Wu, Pan Zhang, Yuhang Zang, Shu Kong, Yuanjun Xiong, Dahua Lin, and Jiaqi Wang. 2023. Alpha-CLIP: A clip model focusing on wherever you want. arXiv preprint arXiv:2312.03818 (2023)."},{"key":"e_1_3_2_1_35_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS. 6000--6010."},{"key":"e_1_3_2_1_36_1","volume-title":"Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation. In CVPR. 2517--2526.","author":"Vu Tuan-Hung","year":"2019","unstructured":"Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Matthieu Cord, and Patrick P\u00e9rez. 2019. Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation. In CVPR. 2517--2526."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Yao Wu Mingwei Xing Yachao Zhang Yuan Xie Jianping Fan Zhongchao Shi and Yanyun Qu. 2023. Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation via Bidirectional Fusion-Then-Distillation. In ACM MM. 490--498.","DOI":"10.1145\/3581783.3612013"},{"key":"e_1_3_2_1_38_1","volume-title":"Perturbed Progressive Learning for Semisupervised Defect Segmentation. TNNLS","author":"Wu Yao","year":"2024","unstructured":"Yao Wu, Mingwei Xing, Yachao Zhang, Yuan Xie, Zongze Wu, and Yanyun Qu. 2024. Perturbed Progressive Learning for Semisupervised Defect Segmentation. TNNLS (2024), 6118--6132."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Aoran Xiao Jiaxing Huang Dayan Guan Fangneng Zhan and Shijian Lu. 2022. Transfer learning from synthetic to real lidar point cloud for semantic segmentation. In AAAI. 2795--2803.","DOI":"10.1609\/aaai.v36i3.20183"},{"key":"e_1_3_2_1_40_1","volume-title":"Shijian Lu, and Eric P Xing.","author":"Xiao Aoran","year":"2023","unstructured":"Aoran Xiao, Jiaxing Huang, Weihao Xuan, Ruijie Ren, Kangcheng Liu, Dayan Guan, Abdulmotaleb El Saddik, Shijian Lu, and Eric P Xing. 2023. 3d semantic segmentation in the wild: Learning generalized models for adverse-condition point clouds. In CVPR. 9382--9392."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Bowei Xing Xianghua Ying Ruibin Wang Jinfa Yang and Taiyan Chen. 2023. Cross-modal contrastive learning for domain adaptation in 3D semantic segmentation. In AAAI. 2974--2982.","DOI":"10.1609\/aaai.v37i3.25400"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Xiaobo Yang and Xiaojin Gong. 2024. Foundation model assisted weakly supervised semantic segmentation. In WACV. 523--532.","DOI":"10.1109\/WACV57701.2024.00058"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Li Yi Boqing Gong and Thomas Funkhouser. 2021. Complete & Label: A domain adaptation approach to semantic segmentation of lidar point clouds. In CVPR. 15363--15373.","DOI":"10.1109\/CVPR46437.2021.01511"},{"key":"e_1_3_2_1_44_1","volume-title":"Prototype-Guided Multitask Adversarial Network for Cross-Domain LiDAR Point Clouds Semantic Segmentation. TGRS","author":"Yuan Zhimin","year":"2023","unstructured":"Zhimin Yuan, Ming Cheng, Wankang Zeng, Yanfei Su, Weiquan Liu, Shangshu Yu, and Cheng Wang. 2023. Prototype-Guided Multitask Adversarial Network for Cross-Domain LiDAR Point Clouds Semantic Segmentation. TGRS (2023), 1--13."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3219853"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Yihan Zeng Chenhan Jiang Jiageng Mao Jianhua Han Chaoqiang Ye Qingqiu Huang Dit-Yan Yeung Zhen Yang Xiaodan Liang and Hang Xu. 2023. CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data. In CVPR. 15244--15253.","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Renrui Zhang Ziyu Guo Wei Zhang Kunchang Li Xupeng Miao Bin Cui Yu Qiao Peng Gao and Hongsheng Li. 2022. PointCLIP: Point cloud understanding by clip. In CVPR. 8552--8562.","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Yachao Zhang Miaoyu Li Yuan Xie Cuihua Li Cong Wang Zhizhong Zhang and Yanyun Qu. 2022. Self-supervised Exclusive Learning for 3D Segmentation with Cross-Modal Unsupervised Domain Adaptation. In ACM MM. 3338--3346.","DOI":"10.1145\/3503161.3547987"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Sicheng Zhao Yezhen Wang Bo Li Bichen Wu Yang Gao Pengfei Xu Trevor Darrell and Kurt Keutzer. 2021. ePointDA: An end-to-end simulation-to-real domain adaptation framework for lidar point cloud segmentation. In AAAI. 3500--3509.","DOI":"10.1609\/aaai.v35i4.16464"},{"key":"e_1_3_2_1_50_1","volume-title":"Chen Change Loy, and Bo Dai","author":"Zhou Chong","year":"2022","unstructured":"Chong Zhou, Chen Change Loy, and Bo Dai. 2022. Extract free dense labels from clip. In ECCV. 696--712."},{"key":"e_1_3_2_1_51_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Conditional prompt learning for vision-language models. In CVPR. 16816--16825."},{"key":"e_1_3_2_1_52_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Learning to prompt for vision-language models. IJCV (2022), 2337--2348."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680582","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680582"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3664647.3680582","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680582","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}