{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:39:59Z","timestamp":1773772799868,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62250410368"],"award-info":[{"award-number":["62250410368"]}]},{"name":"Shanghai Key Research Laboratory of NSAI"},{"name":"Nanjing First Automobile Works Grant"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611699","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"7686-7695","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":42,"title":["What2comm: Towards Communication-efficient Collaborative Perception via Feature Decoupling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-2200","authenticated-orcid":false,"given":"Kun","family":"Yang","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-5671","authenticated-orcid":false,"given":"Dingkang","family":"Yang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5339-5603","authenticated-orcid":false,"given":"Jingyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7035-6008","authenticated-orcid":false,"given":"Hanqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8356-1329","authenticated-orcid":false,"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"Duke Kunshan University, Kunshan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8143-9052","authenticated-orcid":false,"given":"Liang","family":"Song","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Advances in Neural Information Processing Systems (NIPS)","volume":"29","author":"Bousmalis Konstantinos","year":"2016","unstructured":"Konstantinos Bousmalis, George Trigeorgis, Nathan Silberman, Dilip Krishnan, and Dumitru Erhan. 2016. Domain separation networks. In Advances in Neural Information Processing Systems (NIPS), Vol. 29."},{"key":"e_1_3_2_1_2_1","volume-title":"CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving. arXiv preprint arXiv:2206.04028","author":"Chen Runjian","year":"2022","unstructured":"Runjian Chen, Yao Mu, Runsen Xu, Wenqi Shao, Chenhan Jiang, Hang Xu, Zhenguo Li, and Ping Luo. 2022b. CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving. arXiv preprint arXiv:2206.04028 (2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_31"},{"key":"e_1_3_2_1_4_1","volume-title":"Conference on Robot Learning (CoRL). PMLR, 1--16","author":"Dosovitskiy Alexey","year":"2017","unstructured":"Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An open urban driving simulator. In Conference on Robot Learning (CoRL). PMLR, 1--16."},{"key":"e_1_3_2_1_5_1","volume-title":"Learning Associative Representation for Facial Expression Recognition. In IEEE International Conference on Image Processing (ICIP). 889--893","author":"Du Yangtao","year":"2021","unstructured":"Yangtao Du, Dingkang Yang, Peng Zhai, Mingchen Li, and Lihua Zhang. 2021. Learning Associative Representation for Facial Expression Recognition. In IEEE International Conference on Image Processing (ICIP). 889--893."},{"key":"e_1_3_2_1_6_1","unstructured":"Yue Hu Shaoheng Fang Zixing Lei Yiqi Zhong and Siheng Chen. 2022. Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps. In Advances in Neural Information Processing Systems (NIPS)."},{"key":"e_1_3_2_1_7_1","volume-title":"Collaboration Helps Camera Overtake LiDAR in 3D Detection. arXiv preprint arXiv:2303.13560","author":"Hu Yue","year":"2023","unstructured":"Yue Hu, Yifan Lu, Runsheng Xu, Weidi Xie, Siheng Chen, and Yanfeng Wang. 2023. Collaboration Helps Camera Overtake LiDAR in 3D Detection. arXiv preprint arXiv:2303.13560 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 2649--2658","author":"Kim Hyunjik","year":"2018","unstructured":"Hyunjik Kim and Andriy Mnih. 2018. Disentangling by factorising. In International Conference on Machine Learning (ICML). PMLR, 2649--2658."},{"key":"e_1_3_2_1_9_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR).","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_10_1","volume-title":"Towards Simultaneous Segmentation Of Liver Tumors And Intrahepatic Vessels Via Cross-Attention Mechanism. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 1--5.","author":"Kuang Haopeng","year":"2023","unstructured":"Haopeng Kuang, Dingkang Yang, Shunli Wang, Xiaoying Wang, and Lihua Zhang. 2023. Towards Simultaneous Segmentation Of Liver Tumors And Intrahepatic Vessels Via Cross-Attention Mechanism. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 1--5."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"e_1_3_2_1_12_1","volume-title":"Text-oriented Modality Reinforcement Network for Multimodal Sentiment Analysis from Unaligned Multimodal Sequences. arXiv preprint arXiv:2307.13205","author":"Lei Yuxuan","year":"2023","unstructured":"Yuxuan Lei, Dingkang Yang, Mingcheng Li, Shunli Wang, Jiawei Chen, and Lihua Zhang. 2023. Text-oriented Modality Reinforcement Network for Multimodal Sentiment Analysis from Unaligned Multimodal Sequences. arXiv preprint arXiv:2307.13205 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_19"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3260040"},{"key":"e_1_3_2_1_15_1","first-page":"29541","article-title":"Learning distilled collaboration graph for multi-agent perception","volume":"34","author":"Li Yiming","year":"2021","unstructured":"Yiming Li, Shunli Ren, Pengxiang Wu, Siheng Chen, Chen Feng, and Wenjun Zhang. 2021. Learning distilled collaboration graph for multi-agent perception. Advances in Neural Information Processing Systems (NIPS), Vol. 34 (2021), 29541--29552.","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Siao Liu Zhaoyu Chen Yang Liu Yuzheng Wang Zhao Zhile Yang Dingkang Ziqing Zhou Xie Yi Wei Li Wenqiang Zhang and Gan Zhongxue. 2023 a. Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation. arXiv preprint arXiv:2308.01194 (2023).","DOI":"10.1109\/ICCV51070.2023.02142"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3298476"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859727"},{"key":"e_1_3_2_1_21_1","volume-title":"2023 c. Generalized video anomaly event detection: Systematic taxonomy and comparison of deep models. arXiv preprint arXiv:2302.05087","author":"Liu Yang","year":"2023","unstructured":"Yang Liu, Dingkang Yang, Yan Wang, Jing Liu, and Liang Song. 2023 c. Generalized video anomaly event detection: Systematic taxonomy and comparison of deep models. arXiv preprint arXiv:2302.05087 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00416"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548197"},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 2642--2651","author":"Odena Augustus","year":"2017","unstructured":"Augustus Odena, Christopher Olah, and Jonathon Shlens. 2017. Conditional image synthesis with auxiliary classifier gans. In International Conference on Machine Learning (ICML). PMLR, 2642--2651."},{"key":"e_1_3_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems (NIPS)","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems (NIPS), Vol. 32 (2019)."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 652--660","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 652--660."},{"key":"e_1_3_2_1_27_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI)","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, 234--241."},{"key":"e_1_3_2_1_28_1","volume-title":"Conference on Robot Learning (CoRL). PMLR, 1195--1210","author":"Vadivelu Nicholas","year":"2021","unstructured":"Nicholas Vadivelu, Mengye Ren, James Tu, Jingkang Wang, and Raquel Urtasun. 2021. Learning to communicate and correct pose errors. In Conference on Robot Learning (CoRL). PMLR, 1195--1210."},{"key":"e_1_3_2_1_29_1","volume-title":"Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization. arXiv preprint arXiv:2211.11236","author":"Wang Jiafeng","year":"2022","unstructured":"Jiafeng Wang, Zhaoyu Chen, Kaixun Jiang, Dingkang Yang, Lingyi Hong, Yan Wang, and Wenqiang Zhang. 2022. Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization. arXiv preprint arXiv:2211.11236 (2022)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475438"},{"key":"e_1_3_2_1_31_1","volume-title":"UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework. arXiv preprint arXiv:2303.12400","author":"Wang Tianhang","year":"2023","unstructured":"Tianhang Wang, Guang Chen, Kai Chen, Zhengfa Liu, Bo Zhang, Alois Knoll, and Changjun Jiang. 2023. UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework. arXiv preprint arXiv:2303.12400 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_36"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019005"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161384"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161460"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564825"},{"key":"e_1_3_2_1_37_1","volume-title":"Bridging the domain gap for multi-agent perception. arXiv preprint arXiv:2210.08451","author":"Xu Runsheng","year":"2022","unstructured":"Runsheng Xu, Jinlong Li, Xiaoyu Dong, Hongkai Yu, and Jiaqi Ma. 2022a. Bridging the domain gap for multi-agent perception. arXiv preprint arXiv:2210.08451 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Conference on Robot Learning (CoRL).","author":"Xu Runsheng","year":"2022","unstructured":"Runsheng Xu, Zhengzhong Tu, Hao Xiang, Wei Shao, Bolei Zhou, and Jiaqi Ma. 2022b. CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers. In Conference on Robot Learning (CoRL)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01318"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3210836"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_9"},{"key":"e_1_3_2_1_46_1","volume-title":"Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception. arXiv preprint arXiv:2307.13933","author":"Yang Dingkang","year":"2023","unstructured":"Dingkang Yang, Shuai Huang, Zhi Xu, Zhenpeng Li, Shunli Wang, Mingcheng Li, Yuzheng Wang, Yang Liu, Kun Yang, Zhaoyu Chen, et al. 2023 b. AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception. arXiv preprint arXiv:2307.13933 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547755"},{"key":"e_1_3_2_1_48_1","volume-title":"2023 c. Target and source modality co-reinforcement for emotion understanding from asynchronous multimodal sequences. Knowledge-Based Systems","author":"Yang Dingkang","year":"2023","unstructured":"Dingkang Yang, Yang Liu, Can Huang, Mingcheng Li, Xiao Zhao, Yuzheng Wang, Kun Yang, Yan Wang, Peng Zhai, and Lihua Zhang. 2023 c. Target and source modality co-reinforcement for emotion understanding from asynchronous multimodal sequences. Knowledge-Based Systems 2023), 110370."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095027"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00098"},{"key":"e_1_3_2_1_51_1","volume-title":"2023 e. Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception. arXiv preprint arXiv:2307.13929","author":"Yang Kun","year":"2023","unstructured":"Kun Yang, Dingkang Yang, Jingyu Zhang, Mingcheng Li, Yang Liu, Jing Liu, Hanqi Wang, Peng Sun, and Liang Song. 2023 e. Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception. arXiv preprint arXiv:2307.13929 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"e_1_3_2_1_53_1","volume-title":"Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow Prediction. arXiv preprint arXiv:2303.10552","author":"Yu Haibao","year":"2023","unstructured":"Haibao Yu, Yingjuan Tang, Enze Xie, Jilei Mao, Jirui Yuan, Ping Luo, and Zaiqing Nie. 2023. Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow Prediction. arXiv preprint arXiv:2303.10552 (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01099"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"e_1_3_2_1_56_1","volume-title":"Central moment discrepancy (cmd) for domain-invariant representation learning. arXiv preprint arXiv:1702.08811","author":"Zellinger Werner","year":"2017","unstructured":"Werner Zellinger, Thomas Grubinger, Edwin Lughofer, Thomas Natschl\u00e4ger, and Susanne Saminger-Platz. 2017. Central moment discrepancy (cmd) for domain-invariant representation learning. arXiv preprint arXiv:1702.08811 (2017)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3104166"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097060"},{"key":"e_1_3_2_1_59_1","volume-title":"Direct field-to-pattern monolithic design of holographic metasurface via residual encoder-decoder convolutional neural network. Opto-Electronic Advances","author":"Zhu Ruichao","year":"2023","unstructured":"Ruichao Zhu, Jiafu Wang, Tianshuo Qiu, Dingkang Yang, Bo Feng, Zuntian Chu, Tonghao Liu, Yajuan Han, Hongya Chen, and Shaobo Qu. 2023. Direct field-to-pattern monolithic design of holographic metasurface via residual encoder-decoder convolutional neural network. Opto-Electronic Advances (2023), 220148-1."},{"key":"e_1_3_2_1_60_1","volume-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations (ICLR).","author":"Zhu Xizhou","year":"2021","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2021. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations (ICLR)."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611699","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:58:01Z","timestamp":1755820681000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611699"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":60,"alternative-id":["10.1145\/3581783.3611699","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611699","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}