{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T05:24:38Z","timestamp":1751520278494,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society"},{"name":"Presidential Fund from the Chinese University of Hong Kong, Shenzhen"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475315","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T04:59:18Z","timestamp":1634533158000},"page":"1712-1720","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Few-Shot Multi-Agent Perception"],"prefix":"10.1145","author":[{"given":"Chenyou","family":"Fan","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Huang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294958"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305404"},{"volume-title":"On the differentiability of the solution to convex optimization problems. arXiv preprint arXiv:1804.05098","year":"2018","author":"Barratt Shane","key":"e_1_3_2_2_3_1"},{"volume-title":"Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587","year":"2017","author":"Chen Liang-Chieh","key":"e_1_3_2_2_4_1"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999868"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999868"},{"volume-title":"Tarmac: Targeted multi-agent communication. In ICML.","year":"2019","author":"Das Abhishek","key":"e_1_3_2_2_7_1"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3073897"},{"volume-title":"Federated Few-Shot Learning with Adversarial Learning. arXiv preprint arXiv:2104.00365","year":"2021","author":"Fan Chenyou","key":"e_1_3_2_2_9_1"},{"volume-title":"Yong Jae Lee, David J Crandall, and Michael S Ryoo.","year":"2017","author":"Fan Chenyou","key":"e_1_3_2_2_10_1"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305498"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157336"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Spyros Gidaris and Nikos Komodakis. 2018. Dynamic Few-Shot Visual Learning Without Forgetting. In CVPR.  Spyros Gidaris and Nikos Komodakis. 2018. Dynamic Few-Shot Visual Learning Without Forgetting. In CVPR.","DOI":"10.1109\/CVPR.2018.00459"},{"volume-title":"Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment","author":"Guo Xiyue","key":"e_1_3_2_2_14_1"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413811"},{"key":"e_1_3_2_2_16_1","unstructured":"Kaiming He Georgia Gkioxari Piotr Doll\u00e1r and Ross Girshick. 2017. Mask R-CNN. In ICCV.  Kaiming He Georgia Gkioxari Piotr Doll\u00e1r and Ross Girshick. 2017. Mask R-CNN. In ICCV."},{"key":"e_1_3_2_2_17_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Chiori Hori Takaaki Hori Teng-Yok Lee Ziming Zhang Bret Harsham John R Hershey Tim K Marks and Kazuhiko Sumi. 2017. Attention-based multimodal fusion for video description. In ICCV.  Chiori Hori Takaaki Hori Teng-Yok Lee Ziming Zhang Bret Harsham John R Hershey Tim K Marks and Kazuhiko Sumi. 2017. Attention-based multimodal fusion for video description. In ICCV.","DOI":"10.1109\/ICCV.2017.450"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295030"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Unnat Jain Luca Weihs Eric Kolve Mohammad Rastegari Svetlana Lazebnik Ali Farhadi Alexander G Schwing and Aniruddha Kembhavi. 2019. Two body problem: Collaborative visual task completion. In CVPR.  Unnat Jain Luca Weihs Eric Kolve Mohammad Rastegari Svetlana Lazebnik Ali Farhadi Alexander G Schwing and Aniruddha Kembhavi. 2019. Two body problem: Collaborative visual task completion. In CVPR.","DOI":"10.1109\/CVPR.2019.00685"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327757.3327828"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/060659624"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_2_24_1","unstructured":"Aoxue Li Weiran Huang Xu Lan Jiashi Feng Zhenguo Li and Liwei Wang. 2020 a. Boosting Few-Shot Learning With Adaptive Margin Loss. In CVPR.  Aoxue Li Weiran Huang Xu Lan Jiashi Feng Zhenguo Li and Liwei Wang. 2020 a. Boosting Few-Shot Learning With Adaptive Margin Loss. In CVPR."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413944"},{"key":"e_1_3_2_2_26_1","unstructured":"Wenbin Li et al. 2019. Revisiting local descriptor based image-to-class measure for few-shot learning. In CVPR.  Wenbin Li et al. 2019. Revisiting local descriptor based image-to-class measure for few-shot learning. In CVPR."},{"volume-title":"Jordan","year":"2020","author":"Lin Tianyi","key":"e_1_3_2_2_27_1"},{"key":"e_1_3_2_2_28_1","unstructured":"T. Lin N. Ho and M. Jordan. 2019 a. On efficient optimal transport: An analysis of greedy and accelerated mirror descent algorithms. In ICML. 3982--3991.  T. Lin N. Ho and M. Jordan. 2019 a. On efficient optimal transport: An analysis of greedy and accelerated mirror descent algorithms. In ICML. 3982--3991."},{"volume-title":"2019 b. On the acceleration of the Sinkhorn and Greenkhorn algorithms for optimal transport. ArXiv Preprint","year":"1906","author":"Lin T.","key":"e_1_3_2_2_29_1"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413915"},{"key":"e_1_3_2_2_31_1","unstructured":"Yen-Cheng Liu Junjiao Tian Nathaniel Glaser and Zsolt Kira. 2020 b. When2com: Multi-Agent Perception via Communication Graph Grouping. In CVPR.  Yen-Cheng Liu Junjiao Tian Nathaniel Glaser and Zsolt Kira. 2020 b. When2com: Multi-Agent Perception via Communication Graph Grouping. In CVPR."},{"key":"e_1_3_2_2_32_1","unstructured":"Yen-Cheng Liu Junjiao Tian Chih-Yao Ma Nathan Glaser Chia-Wen Kuo and Zsolt Kira. 2020 c. Who2com: Collaborative perception via learnable handshake communication. (2020).  Yen-Cheng Liu Junjiao Tian Chih-Yao Ma Nathan Glaser Chia-Wen Kuo and Zsolt Kira. 2020 c. Who2com: Collaborative perception via learnable handshake communication. (2020)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Jonathan Long Evan Shelhamer and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In CVPR.  Jonathan Long Evan Shelhamer and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Minh-Thang Luong Hieu Pham and Christopher D Manning. 2015. Effective approaches to attention-based neural machine translation. (2015).  Minh-Thang Luong Hieu Pham and Christopher D Manning. 2015. Effective approaches to attention-based neural machine translation. (2015).","DOI":"10.18653\/v1\/D15-1166"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327010"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"O. Pele and M. Werman. 2009. Fast and robust earth mover's distances. In ICCV.  O. Pele and M. Werman. 2009. Fast and robust earth mover's distances. In ICCV.","DOI":"10.1109\/ICCV.2009.5459199"},{"volume-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games. arXiv preprint arXiv:1703.10069","year":"2017","author":"Peng Peng","key":"e_1_3_2_2_38_1"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Zhimao Peng Zechao Li Junge Zhang Yan Li Guo-Jun Qi and Jinhui Tang. 2019. Few-Shot Image Recognition With Knowledge Transfer. In ICCV.  Zhimao Peng Zechao Li Junge Zhang Yan Li Guo-Jun Qi and Jinhui Tang. 2019. Few-Shot Image Recognition With Knowledge Transfer. In ICCV.","DOI":"10.1109\/ICCV.2019.00053"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298184"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Joseph Redmon Santosh Divvala Ross Girshick and Ali Farhadi. 2016. You only look once: Unified real-time object detection. In CVPR.  Joseph Redmon Santosh Divvala Ross Girshick and Ali Farhadi. 2016. You only look once: Unified real-time object detection. In CVPR.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/938978.939133"},{"volume-title":"Airsim: High-fidelity visual and physical simulation for autonomous vehicles. In Field and service robotics.","year":"2018","author":"Shah Shital","key":"e_1_3_2_2_44_1"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/2968826.2968890"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157348"},{"volume-title":"Meta-transfer learning for few-shot learning. CVPR","year":"2019","author":"Sun Qianru","key":"e_1_3_2_2_48_1"},{"volume-title":"Dynamic Digital Twin and Federated Learning with Incentives for Air-Ground Networks","year":"2020","author":"Sun Wen","key":"e_1_3_2_2_49_1"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"crossref","unstructured":"Flood Sung et al. 2018. Learning to compare: Relation network for few-shot learning. CVPR (2018).  Flood Sung et al. 2018. Learning to compare: Relation network for few-shot learning. CVPR (2018).","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091529.3091572"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413884"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"crossref","unstructured":"G. Tzanetakis and P. Cook. 2002. Musical genre classification of audio signals\". IEEE Transactions on Speech and Audio Processing\" (2002).  G. Tzanetakis and P. Cook. 2002. Musical genre classification of audio signals\". IEEE Transactions on Speech and Audio Processing\" (2002).","DOI":"10.1109\/TSA.2002.800560"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157504"},{"volume-title":"Yingtian Zou, Daquan Zhou, and Jiashi Feng.","year":"2019","author":"Wang Kaixin","key":"e_1_3_2_2_57_1"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3083263"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413946"},{"volume":"201","journal-title":"David J Crandall.","author":"Xu Mingze","key":"e_1_3_2_2_60_1"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"crossref","unstructured":"Matthew D Zeiler Dilip Krishnan Graham W Taylor and Rob Fergus. 2010. Deconvolutional networks. In CVPR.  Matthew D Zeiler Dilip Krishnan Graham W Taylor and Rob Fergus. 2010. Deconvolutional networks. In CVPR.","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"crossref","unstructured":"Chi Zhang Yujun Cai Guosheng Lin and Chunhua Shen. 2020. DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers. In CVPR.  Chi Zhang Yujun Cai Guosheng Lin and Chunhua Shen. 2020. DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"crossref","unstructured":"Peng Zhao and Zhi-Hua Zhou. 2018. Label distribution learning by optimal transport. In AAAI.  Peng Zhao and Zhi-Hua Zhou. 2018. Label distribution learning by optimal transport. In AAAI.","DOI":"10.1609\/aaai.v32i1.11609"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.299"}],"event":{"name":"MM '21: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Virtual Event China","acronym":"MM '21"},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475315","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:18Z","timestamp":1750193358000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":64,"alternative-id":["10.1145\/3474085.3475315","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475315","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}