{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:58:34Z","timestamp":1783529914077,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":49,"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":"Public Welfare Technology Research Project of Zhejiang Province","award":["LGF21F020010"],"award-info":[{"award-number":["LGF21F020010"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976188"],"award-info":[{"award-number":["61976188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Pioneer and Leading Goose R&D Program of Zhejiang","award":["2023C01212"],"award-info":[{"award-number":["2023C01212"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612279","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"7283-7294","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Lite-MKD: A Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7718-5443","authenticated-orcid":false,"given":"Baolong","family":"Liu","sequence":"first","affiliation":[{"name":"Zhejiang Gongshang University & Zhejiang Key Lab of E-Commerce, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7932-6031","authenticated-orcid":false,"given":"Tianyi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7026-6730","authenticated-orcid":false,"given":"Peng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-4508","authenticated-orcid":false,"given":"Daizong","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4907-3978","authenticated-orcid":false,"given":"Xiaoye","family":"Qu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-5497","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5244-3274","authenticated-orcid":false,"given":"Jianfeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University & Zhejiang Key Lab of E-Commerce, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5566-4689","authenticated-orcid":false,"given":"Xun","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University & Zhejiang Key Lab of E-Commerce, 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":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018","author":"Bhat Shariq Farooq","year":"2021","unstructured":"Shariq Farooq Bhat, Ibraheem Alhashim, and Peter Wonka. 2021. Adabins: Depth estimation using adaptive bins. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018."},{"key":"e_1_3_2_1_2_1","volume-title":"Tarn: Temporal attentive relation network for few-shot and zero-shot action recognition. arXiv preprint arXiv:1907.09021","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. arXiv preprint arXiv:1907.09021 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00888"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"e_1_3_2_1_9_1","volume-title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","author":"Fang Hao-Shu","year":"2022","unstructured":"Hao-Shu Fang, Jiefeng Li, Hongyang Tang, Chao Xu, Haoyi Zhu, Yuliang Xiu, Yong-Lu Li, and Cewu Lu. 2022. AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 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. PMLR, 1126--1135."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547995"},{"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":"10.1109\/CVPR52688.2022.01937"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169842"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3221292"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00912"},{"key":"e_1_3_2_1_21_1","volume-title":"Knowledge distillation from a stronger teacher. arXiv preprint arXiv:2205.10536","author":"Huang Tao","year":"2022","unstructured":"Tao Huang, Shan You, Fei Wang, Chen Qian, and Chang Xu. 2022. Knowledge distillation from a stronger teacher. arXiv preprint arXiv:2205.10536 (2022)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479232"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01346"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_1_26_1","volume-title":"One-shot learning by inverting a compositional causal process. Advances in neural information processing systems","author":"Lake Brenden M","year":"2013","unstructured":"Brenden M Lake, Russ R Salakhutdinov, and Josh Tenenbaum. 2013. One-shot learning by inverting a compositional causal process. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_27_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_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238514"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547782"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"e_1_3_2_1_33_1","volume-title":"Tel Aviv","author":"Nguyen Khoi D","year":"2022","unstructured":"Khoi D Nguyen, Quoc-Huy Tran, Khoi Nguyen, Binh-Son Hua, and Rang Nguyen. 2022. Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XX. Springer, 471--487."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"e_1_3_2_1_35_1","volume-title":"Self-training For Few-shot Transfer Across Extreme Task Differences. In International Conference on Learning Representations.","author":"Phoo Cheng Perng","year":"2020","unstructured":"Cheng Perng Phoo and Bharath Hariharan. 2020. Self-training For Few-shot Transfer Across Extreme Task Differences. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16356"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"e_1_3_2_1_38_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_39_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_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475218"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01285"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3086140"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00325"},{"key":"e_1_3_2_1_46_1","volume-title":"Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization. arXiv preprint arXiv:2306.07576","author":"Yang Yuheng","year":"2023","unstructured":"Yuheng Yang, Haipeng Chen, Zhenguang Liu, Yingda Lyu, Beibei Zhang, Shuang Wu, Zhibo Wang, and Kui Ren. 2023. Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization. arXiv preprint arXiv:2306.07576 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Philip HS Torr, and Piotr Koniusz","author":"Zhang Hongguang","year":"2020","unstructured":"Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip HS Torr, and Piotr Koniusz. 2020. Few-shot action recognition with permutation-invariant attention. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part V 16. Springer, 525--542."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.316"}],"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\/3581783.3612279","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:07:12Z","timestamp":1755821232000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612279"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":49,"alternative-id":["10.1145\/3581783.3612279","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612279","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"}}]}}