{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:14:22Z","timestamp":1765008862188,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2023AFB294"],"award-info":[{"award-number":["2023AFB294"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770978","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:11Z","timestamp":1765008491000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CPR-CLIP: Cross-modal Consistent and Prompt-diverse Regularized CLIP for Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3497-0381","authenticated-orcid":false,"given":"Hao","family":"Song","sequence":"first","affiliation":[{"name":"the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4142-4833","authenticated-orcid":false,"given":"Yangjun","family":"Ou","sequence":"additional","affiliation":[{"name":"the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2375-3332","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"4","volume-title":"International Conference on Machine Learning","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In International Conference on Machine Learning. 4."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696409.3700204"},{"key":"e_1_3_3_1_5_2","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02329"},{"key":"e_1_3_3_1_9_2","volume-title":"International Conference on Learning Representations","author":"Huang Xiaohu","year":"2024","unstructured":"Xiaohu Huang, Hao Zhou, Kun Yao, and Kai Han. 2024. FROSTER: Frozen CLIP is a Strong Teacher for Open-Vocabulary Action Recognition. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"e_1_3_3_1_13_2","first-page":"74","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Kim Minji","year":"2024","unstructured":"Minji Kim, Dongyoon Han, Taekyung Kim, and Bohyung Han. 2024. Leveraging temporal contextualization for video action recognition. In Proceedings of the European Conference on Computer Vision. 74\u201391."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00471"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Zhenzhen Quan Jialei Chen Daisuke Deguchi Jie Sun Chenkai Zhang Yujun Li and Hiroshi Murase. 2025. Semantic matters: A constrained approach for zero-shot video action recognition. Pattern Recognition (2025) 111402.","DOI":"10.1016\/j.patcog.2025.111402"},{"key":"e_1_3_3_1_21_2","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_3_1_22_2","first-page":"8748","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"e_1_3_3_1_24_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems (2014)."},{"key":"e_1_3_3_1_25_2","unstructured":"Khurram Soomro Amir\u00a0Roshan Zamir and Mubarak Shah. 2012. Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1212.0402 (2012)."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28347"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Mengmeng Wang Jiazheng Xing Jianbiao Mei Yong Liu and Yunliang Jiang. 2021. ActionCLIP: Adapting Language-Image Pretrained Models for Video Action Recognition. IEEE Transactions on Neural Networks and Learning Systems (2021) 625\u2013637.","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Mengmeng Wang Jiazheng Xing Jianbiao Mei Yong Liu and Yunliang Jiang. 2025. ActionCLIP: Adapting Language-Image Pretrained Models for Video Action Recognition. IEEE Transactions on Neural Networks and Learning Systems (2025) 625\u2013637.","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00846"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Yu Zhang Zhengjie Chen Tianyu Xu Junjie Zhao Siya Mi Xin Geng and Min-Ling Zhang. 2024. Temporal segment dropout for human action video recognition. Pattern Recognition (2024) 109985.","DOI":"10.1016\/j.patcog.2023.109985"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Kaiyang Zhou Jingkang Yang Chen\u00a0Change Loy and Ziwei Liu. 2022. Learning to Prompt for Vision-Language Models. International Journal of Computer Vision (2022) 2337\u20132348.","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671690"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:10:26Z","timestamp":1765008626000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770978"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":34,"alternative-id":["10.1145\/3743093.3770978","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770978","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}