{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T22:24:27Z","timestamp":1784413467034,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":47,"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":"the Natural Science Foundation of China","award":["U1909203, 62036009, 62276237, 62206250"],"award-info":[{"award-number":["U1909203, 62036009, 62276237, 62206250"]}]},{"name":"the Ten Thousand Talent Program of Zhejiang Province"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612380","type":"proceedings-article","created":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T10:35:09Z","timestamp":1698921309000},"page":"2344-2352","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Multi-Speed Global Contextual Subspace Matching for Few-Shot Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1766-8683","authenticated-orcid":false,"given":"Tianwei","family":"Yu","sequence":"first","affiliation":[{"name":"Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6122-0574","authenticated-orcid":false,"given":"Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8302-1338","authenticated-orcid":false,"given":"Yuanjie","family":"Dang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2555-343X","authenticated-orcid":false,"given":"Ruohong","family":"Huan","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2077-9608","authenticated-orcid":false,"given":"Ronghua","family":"Liang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"30th British Machine Vision Conference.","author":"Bishay Mina","year":"2019","unstructured":"Mina Bishay, Georgios Zoumpourlis, and Ioannis Patras. 2019. TARN: Temporal attentive relation network for few-shot and zero-shot action recognition. In 30th British Machine Vision Conference."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Learning Representations.","author":"Chen Wei-Yu","year":"2019","unstructured":"Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. 2019. A Closer Look at Few-shot Classification. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00234"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00669"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_8_1","volume-title":"ProtoGAN: Towards Few Shot Learning for Action Recognition. In 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW). 1308--1316","author":"Dwivedi Sai Kumar","year":"2019","unstructured":"Sai Kumar Dwivedi, Vikram Gupta, Rahul Mitra, Shuaib Ahmed, and Arjun Jain. 2019. ProtoGAN: Towards Few Shot Learning for Action Recognition. In 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW). 1308--1316."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_1_10_1","volume-title":"SlowFast Networks for Video Recognition. In 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE, 6201--6210","author":"Feichtenhofer Christoph","year":"2019","unstructured":"Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. 2019. SlowFast Networks for Video Recognition. In 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE, 6201--6210."},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. 1126--1135","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning. 1126--1135."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413502"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0833-x"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107164"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00605"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"36","author":"Fei Mengjuan","year":"2022","unstructured":"Shuyuan Li, Huabin Liu, Rui Qian, Yuxi Li, John See, Mengjuan Fei, Xiaoyuan Yu, and Weiyao Lin. 2022. TA2N: Two-stage action alignment network for few-shot action recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 1404--1411."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 30th ACM International Conference on Multimedia. 6230--6240","author":"Lin Weiyao","year":"2022","unstructured":"Huabin Liu, Weixian Lv, John See, and Weiyao Lin. 2022. Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition. In Proceedings of the 30th ACM International Conference on Multimedia. 6230--6240."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.01.004"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00047"},{"key":"e_1_3_2_1_23_1","volume-title":"On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999","author":"Nichol Alex","year":"2018","unstructured":"Alex Nichol, Joshua Achiam, and John Schulman. 2018. On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999 (2018)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_1_25_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","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, Vol. 32 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"e_1_3_2_1_28_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems","author":"Snell Jake","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30."},{"key":"e_1_3_2_1_29_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_3_2_1_31_1","volume-title":"Learning to learn: Meta-critic networks for sample efficient learning. arXiv preprint arXiv:1706.09529","author":"Sung Flood","year":"2017","unstructured":"Flood Sung, Li Zhang, Tao Xiang, Timothy Hospedales, and Yongxin Yang. 2017. Learning to learn: Meta-critic networks for sample efficient learning. arXiv preprint arXiv:1706.09529 (2017)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 586--591","author":"Turk M.A.","unstructured":"M.A. Turk and A.P. Pentland. 1991. Face recognition using eigenfaces. In Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 586--591."},{"key":"e_1_3_2_1_35_1","unstructured":"Oriol Vinyals Charles Blundell Timothy Lillicrap Daan Wierstra et al. 2016. Matching networks for one shot learning. Advances in neural information processing systems Vol. 29."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00829"},{"key":"e_1_3_2_1_37_1","volume-title":"Temporal segment networks for action recognition in videos","author":"Wang Limin","year":"2018","unstructured":"Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, and Luc Van Gool. 2018. Temporal segment networks for action recognition in videos. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 11 (2018), 2740--2755."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.57"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"e_1_3_2_1_41_1","volume-title":"Simpleshot: Revisiting nearest-neighbor classification for few-shot learning. arXiv preprint arXiv:1911.04623","author":"Wang Yan","year":"2019","unstructured":"Yan Wang, Wei-Lun Chao, Kilian Q Weinberger, and Laurens van der Maaten. 2019. Simpleshot: Revisiting nearest-neighbor classification for few-shot learning. arXiv preprint arXiv:1911.04623 (2019)."},{"key":"e_1_3_2_1_42_1","volume-title":"Power normalizing second-order similarity network for few-shot learning. In 2019 IEEE winter conference on applications of computer vision (WACV)","author":"Zhang Hongguang","unstructured":"Hongguang Zhang and Piotr Koniusz. 2019. Power normalizing second-order similarity network for few-shot learning. In 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, 1185--1193."},{"key":"e_1_3_2_1_43_1","volume-title":"Multi-level second-order few-shot learning","author":"Zhang Hongguang","unstructured":"Hongguang Zhang, Hongdong Li, and Piotr Koniusz. 2022. Multi-level second-order few-shot learning. IEEE Transactions on Multimedia, Vol. Early Access (2022)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"e_1_3_2_1_45_1","volume-title":"Learning Implicit Temporal Alignment for Few-shot Video Classification. In International Joint Conference on Artificial Intelligence.","author":"Zhang Songyang","year":"2021","unstructured":"Songyang Zhang, Jiale Zhou, and Xuming He. 2021. Learning Implicit Temporal Alignment for Few-shot Video Classification. In International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00172"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"}],"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\/3581783.3612380","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:56:11Z","timestamp":1755820571000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612380"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":47,"alternative-id":["10.1145\/3581783.3612380","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612380","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"}}]}}