{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:25:16Z","timestamp":1765308316375,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","funder":[{"name":"Hong Kong RIF","award":["No. R6021-20"],"award-info":[{"award-number":["No. R6021-20"]}]},{"name":"Hong Kong CRF","award":["Grant No. C2004-21G and C7004-22G"],"award-info":[{"award-number":["Grant No. C2004-21G and C7004-22G"]}]},{"name":"the Postdoctoral Fellowship Program of CPSF","award":["Grant Number GZC20232292"],"award-info":[{"award-number":["Grant Number GZC20232292"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755088","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"3448-3457","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2290-0944","authenticated-orcid":false,"given":"Penglei","family":"Sun","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8146-2236","authenticated-orcid":false,"given":"Yaoxian","family":"Song","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7308-3642","authenticated-orcid":false,"given":"Xiangru","family":"Zhu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2639-1804","authenticated-orcid":false,"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guang Zhou)), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2986-967X","authenticated-orcid":false,"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7445-5632","authenticated-orcid":false,"given":"Yue","family":"Liu","sequence":"additional","affiliation":[{"name":"Terminus Technologies Co., Ltd., Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9594-5693","authenticated-orcid":false,"given":"Changqun","family":"Xia","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0265-3454","authenticated-orcid":false,"given":"Tiefeng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0608-9408","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Hong Kong (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9745-4372","authenticated-orcid":false,"given":"Xiaowen","family":"Chu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"e_1_3_2_1_2_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"e_1_3_2_1_6_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023a. Qwen Technical Report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023b. Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs16091477"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02061"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"e_1_3_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Chen Runnan","year":"2024","unstructured":"Runnan Chen, Youquan Liu, Lingdong Kong, Nenglun Chen, Xinge Zhu, Yuexin Ma, Tongliang Liu, and Wenping Wang. 2024b. Towards label-free scene understanding by vision foundation models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"e_1_3_2_1_16_1","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys.org (accessed","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al., 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys.org (accessed 14 April 2023), Vol. 2, 3 (2023), 6."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_18_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv:2305.06500 [cs.CV]"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"e_1_3_2_1_20_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30761-2"},{"key":"e_1_3_2_1_22_1","volume-title":"Scene-llm: Extending language model for 3d visual understanding and reasoning. arXiv preprint arXiv:2403.11401","author":"Fu Rao","year":"2024","unstructured":"Rao Fu, Jingyu Liu, Xilun Chen, Yixin Nie, and Wenhan Xiong. 2024. Scene-llm: Extending language model for 3d visual understanding and reasoning. arXiv preprint arXiv:2403.11401 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(94)00643-Y"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02494"},{"key":"e_1_3_2_1_26_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01554-9"},{"key":"e_1_3_2_1_28_1","volume-title":"Chat-3d v2: Bridging 3d scene and large language models with object identifiers. arXiv preprint arXiv:2312.08168","author":"Huang Haifeng","year":"2023","unstructured":"Haifeng Huang, Zehan Wang, Rongjie Huang, Luping Liu, Xize Cheng, Yang Zhao, Tao Jin, and Zhou Zhao. 2023. Chat-3d v2: Bridging 3d scene and large language models with object identifiers. arXiv preprint arXiv:2312.08168 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790","author":"Huang Junjie","year":"2021","unstructured":"Junjie Huang, Guan Huang, Zheng Zhu, Yun Ye, and Dalong Du. 2021. Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)."},{"key":"e_1_3_2_1_30_1","volume-title":"Compositional Attention Networks for Machine Reasoning. In International Conference on Learning Representations.","author":"Hudson Drew A","year":"2018","unstructured":"Drew A Hudson and Christopher D Manning. 2018. Compositional Attention Networks for Machine Reasoning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"e_1_3_2_1_33_1","volume-title":"Bilinear attention networks. Advances in neural information processing systems","author":"Kim Jin-Hwa","year":"2018","unstructured":"Jin-Hwa Kim, Jaehyun Jun, and Byoung-Tak Zhang. 2018. Bilinear attention networks. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.889"},{"key":"e_1_3_2_1_35_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00657"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 27831-27840","author":"Kuckreja Kartik","year":"2024","unstructured":"Kartik Kuckreja, Muhammad Sohail Danish, Muzammal Naseer, Abhijit Das, Salman Khan, and Fahad Shahbaz Khan. 2024. Geochat: Grounded large vision-language model for remote sensing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 27831-27840."},{"key":"e_1_3_2_1_38_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW63481.2024.10645462"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_41_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024b. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"e_1_3_2_1_43_1","volume-title":"scale and state strategy: rethinking urban and regional governance. Progress in human geography","author":"MacLeod Gordon","year":"1999","unstructured":"Gordon MacLeod and Mark Goodwin. 1999. Space, scale and state strategy: rethinking urban and regional governance. Progress in human geography, Vol. 23, 4 (1999), 503-527."},{"key":"e_1_3_2_1_44_1","first-page":"689","volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11)","author":"Ngiam Jiquan","year":"2011","unstructured":"Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y Ng. 2011. Multimodal deep learning. In Proceedings of the 28th international conference on machine learning (ICML-11). 689-696."},{"key":"e_1_3_2_1_45_1","volume-title":"Disease-image-specific learning for diagnosis-oriented neuroimage synthesis with incomplete multi-modality data","author":"Pan Yongsheng","year":"2021","unstructured":"Yongsheng Pan, Mingxia Liu, Yong Xia, and Dinggang Shen. 2021. Disease-image-specific learning for diagnosis-oriented neuroimage synthesis with incomplete multi-modality data. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 10 (2021), 6839-6853."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00593"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"e_1_3_2_1_48_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","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, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_49_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Ramakrishnan Santhosh Kumar","year":"2021","unstructured":"Santhosh Kumar Ramakrishnan, Aaron Gokaslan, Erik Wijmans, Oleksandr Maksymets, Alexander Clegg, John M Turner, Eric Undersander, Wojciech Galuba, Andrew Westbury, Angel X Chang, et al., 2021. Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.226"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2019.101872"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. 2992-3006","author":"Song Yaoxian","year":"2022","unstructured":"Yaoxian Song, Penglei Sun, Pengfei Fang, Linyi Yang, Yanghua Xiao, and Yue Zhang. 2022. Human-in-the-loop Robotic Grasping Using BERT Scene Representation. In Proceedings of the 29th International Conference on Computational Linguistics. 2992-3006."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3399746"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.07.003"},{"key":"e_1_3_2_1_55_1","unstructured":"Penglei Sun Yaoxian Song Xiang Liu Xiaofei Yang Qiang Wang YANG Yang Xiaowen Chu et al. 2024a. 3D Question Answering for City Scene Understanding. In ACM Multimedia 2024."},{"key":"e_1_3_2_1_56_1","volume-title":"European Conference on Computer Vision. Springer, 387-404","author":"Sun Penglei","year":"2024","unstructured":"Penglei Sun, Yaoxian Song, Xinglin Pan, Peijie Dong, Xiaofei Yang, Qiang Wang, Zhixu Li, Tiefeng Li, and Xiaowen Chu. 2024b. Multi-Task Domain Adaptation for Language Grounding with 3D Objects. In European Conference on Computer Vision. Springer, 387-404."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920937052"},{"key":"e_1_3_2_1_58_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_59_1","unstructured":"Receivables Management Section U.S Geological Survey. [n.d.]. EarthExplorer. https:\/\/earthexplorer.usgs.gov\/."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28357"},{"key":"e_1_3_2_1_61_1","volume-title":"LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Wang Junjue","year":"2021","unstructured":"Junjue Wang, Zhuo Zheng, Xiaoyan Lu, and Yanfei Zhong. 2021. LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_62_1","volume-title":"Robust Multimodal Learning via Representation Decoupling. arXiv preprint arXiv:2407.04458","author":"Wei Shicai","year":"2024","unstructured":"Shicai Wei, Yang Luo, Yuji Wang, and Chunbo Luo. 2024. Robust Multimodal Learning via Representation Decoupling. arXiv preprint arXiv:2407.04458 (2024)."},{"key":"e_1_3_2_1_63_1","first-page":"3784","article-title":"Debiased visual question answering from feature and sample perspectives","volume":"34","author":"Wen Zhiquan","year":"2021","unstructured":"Zhiquan Wen, Guanghui Xu, Mingkui Tan, Qingyao Wu, and Qi Wu. 2021. Debiased visual question answering from feature and sample perspectives. Advances in Neural Information Processing Systems, Vol. 34 (2021), 3784-3796.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.62"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591508"},{"key":"e_1_3_2_1_66_1","volume-title":"Lidar-llm: Exploring the potential of large language models for 3d lidar understanding. arXiv preprint arXiv:2312.14074","author":"Yang Senqiao","year":"2023","unstructured":"Senqiao Yang, Jiaming Liu, Ray Zhang, Mingjie Pan, Zoey Guo, Xiaoqi Li, Zehui Chen, Peng Gao, Yandong Guo, and Shanghang Zhang. 2023a. Lidar-llm: Exploring the potential of large language models for 3d lidar understanding. arXiv preprint arXiv:2312.14074 (2023)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6996"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs15153871"},{"key":"e_1_3_2_1_72_1","first-page":"1","article-title":"Mutual attention inception network for remote sensing visual question answering","volume":"60","author":"Zheng Xiangtao","year":"2021","unstructured":"Xiangtao Zheng, Binqiang Wang, Xingqian Du, and Xiaoqiang Lu. 2021. Mutual attention inception network for remote sensing visual question answering. IEEE Transactions on Geoscience and Remote Sensing, Vol. 60 (2021), 1-14.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_73_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Zhou Junsheng","year":"2024","unstructured":"Junsheng Zhou, Jinsheng Wang, Baorui Ma, Yu-Shen Liu, Tiejun Huang, and Xinlong Wang. 2024. Uni3d: Exploring unified 3d representation at scale. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:17Z","timestamp":1765308017000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":74,"alternative-id":["10.1145\/3746027.3755088","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755088","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"}}]}}