{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:05:10Z","timestamp":1780765510055,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Key R&D Project of Shaanxi Province","award":["2023-YBGY-240"],"award-info":[{"award-number":["2023-YBGY-240"]}]},{"name":"Young Talent Fund of Association for Science and Technology in Shaanxi, China","award":["20220117"],"award-info":[{"award-number":["20220117"]}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376217, 62301434"],"award-info":[{"award-number":["62376217, 62301434"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681081","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"9038-9047","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0217-9791","authenticated-orcid":false,"given":"Congqi","family":"Cao","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'An, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9387-8764","authenticated-orcid":false,"given":"Yueran","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'An, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5504-9889","authenticated-orcid":false,"given":"Yating","family":"Yu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'An, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5359-5701","authenticated-orcid":false,"given":"Qinyi","family":"Lv","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'An, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3970-7823","authenticated-orcid":false,"given":"Lingtong","family":"Min","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'An, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'An, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01450"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103250"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3142530"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_6_1","volume-title":"Yu-Chiang Frank Wang, and Jia-Bin Huang","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. arXiv preprint arXiv:1904.04232 (2019)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_8_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_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413502"},{"key":"e_1_3_2_2_10_1","volume-title":"Clip-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision","author":"Gao Peng","year":"2023","unstructured":"Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yongfeng Zhang, Hongsheng Li, and Yu Qiao. 2023. Clip-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision (2023), 1--15."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"e_1_3_2_2_12_1","volume-title":"Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366","author":"He Junxian","year":"2021","unstructured":"Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. 2021. Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366 (2021)."},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_21"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_2_17_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00009"},{"key":"e_1_3_2_2_19_1","volume-title":"International conference on machine learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888--12900."},{"key":"e_1_3_2_2_20_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_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"e_1_3_2_2_22_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_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00254"},{"key":"e_1_3_2_2_24_1","volume-title":"Few-shot action recognition with compromised metric via optimal transport. arXiv preprint arXiv:2104.03737","author":"Lu Su","year":"2021","unstructured":"Su Lu, Han-Jia Ye, and De-Chuan Zhan. 2021. Few-shot action recognition with compromised metric via optimal transport. arXiv preprint arXiv:2104.03737 (2021)."},{"key":"e_1_3_2_2_25_1","volume-title":"Generative adversarial residual pairwise networks for one shot learning. arXiv preprint arXiv:1703.08033","author":"Mehrotra Akshay","year":"2017","unstructured":"Akshay Mehrotra and Ambedkar Dukkipati. 2017. Generative adversarial residual pairwise networks for one shot learning. arXiv preprint arXiv:1703.08033 (2017)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.33.130"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_27"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"e_1_3_2_2_29_1","first-page":"26462","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume":"35","author":"Pan Junting","year":"2022","unstructured":"Junting Pan, Ziyi Lin, Xiatian Zhu, Jing Shao, and Hongsheng Li. 2022. St-adapter: Parameter-efficient image-to-video transfer learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 26462--26477.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00053"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"e_1_3_2_2_32_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_2_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Requeima James","year":"2019","unstructured":"James Requeima, Jonathan Gordon, John Bronskill, Sebastian Nowozin, and Richard E Turner. 2019. Fast and flexible multi-task classification using conditional neural adaptive processes. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_34_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_2_35_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_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings, Part XIV 16","author":"Tian Yonglong","year":"2020","unstructured":"Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B Tenenbaum, and Phillip Isola. 2020. Rethinking few-shot image classification: a good embedding is all you need?. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XIV 16. Springer, 266--282."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"e_1_3_2_2_39_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 (2016)."},{"key":"e_1_3_2_2_40_1","volume-title":"Actionclip: A new paradigm for video action recognition. arXiv preprint arXiv:2109.08472","author":"Wang Mengmeng","year":"2021","unstructured":"Mengmeng Wang, Jiazheng Xing, and Yong Liu. 2021. Actionclip: A new paradigm for video action recognition. arXiv preprint arXiv:2109.08472 (2021)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475253"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01917--4"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00760"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00628"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00781"},{"key":"e_1_3_2_2_51_1","volume-title":"Multimodal Adaptation of CLIP for Few-Shot Action Recognition. arXiv preprint arXiv:2308.01532","author":"Xing Jiazheng","year":"2023","unstructured":"Jiazheng Xing, Mengmeng Wang, Xiaojun Hou, Guang Dai, Jingdong Wang, and Yong Liu. 2023. Multimodal Adaptation of CLIP for Few-Shot Action Recognition. arXiv preprint arXiv:2308.01532 (2023)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25403"},{"key":"e_1_3_2_2_53_1","volume-title":"International Conference on Machine Learning. PMLR, 10617--10627","author":"Xu Jin","year":"2020","unstructured":"Jin Xu, Jean-Francois Ton, Hyunjik Kim, Adam Kosiorek, and Yee Whye Teh. 2020. Metafun: Meta-learning with iterative functional updates. In International Conference on Machine Learning. PMLR, 10617--10627."},{"key":"e_1_3_2_2_54_1","volume-title":"Aim: Adapting image models for efficient video action recognition. arXiv preprint arXiv:2302.03024","author":"Yang Taojiannan","year":"2023","unstructured":"Taojiannan Yang, Yi Zhu, Yusheng Xie, Aston Zhang, Chen Chen, and Mu Li. 2023. Aim: Adapting image models for efficient video action recognition. arXiv preprint arXiv:2302.03024 (2023)."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612380"},{"key":"e_1_3_2_2_57_1","volume-title":"Proceedings, Part V 16","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_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612192"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"e_1_3_2_2_61_1","first-page":"273","article-title":"Label independent memory for semi-supervised few-shot video classification","volume":"44","author":"Zhu Linchao","year":"2020","unstructured":"Linchao Zhu and Yi Yang. 2020. Label independent memory for semi-supervised few-shot video classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 1 (2020), 273--285.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_62_1","volume-title":"Few-shot action recognition with prototype-centered attentive learning. arXiv preprint arXiv:2101.08085","author":"Zhu Xiatian","year":"2021","unstructured":"Xiatian Zhu, Antoine Toisoul, Juan-Manuel Perez-Rua, Li Zhang, Brais Martinez, and Tao Xiang. 2021. Few-shot action recognition with prototype-centered attentive learning. arXiv preprint arXiv:2101.08085 (2021)."},{"key":"e_1_3_2_2_63_1","volume-title":"A closer look at few-shot video classification: A new baseline and benchmark. arXiv preprint arXiv:2110.12358","author":"Zhu Zhenxi","year":"2021","unstructured":"Zhenxi Zhu, Limin Wang, Sheng Guo, and Gangshan Wu. 2021. A closer look at few-shot video classification: A new baseline and benchmark. arXiv preprint arXiv:2110.12358 (2021)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681081","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":63,"alternative-id":["10.1145\/3664647.3681081","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681081","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}