{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:59:51Z","timestamp":1780765191182,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":53,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202311"],"award-info":[{"award-number":["62202311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Excellent Science and Technology Creative Talent Training Program of Shenzhen Municipality","award":["RCBS20221008093224017"],"award-info":[{"award-number":["RCBS20221008093224017"]}]},{"name":"Shenzhen Natural Science Foundation (the Stable Support Plan Program)","award":["20220809180405001"],"award-info":[{"award-number":["20220809180405001"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2023A1515011512"],"award-info":[{"award-number":["2023A1515011512"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612153","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"1840-1850","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Exploring Motion Cues for Video Test-Time Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8694-4245","authenticated-orcid":false,"given":"Runhao","family":"Zeng","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7475-0127","authenticated-orcid":false,"given":"Qi","family":"Deng","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1224-3080","authenticated-orcid":false,"given":"Huixuan","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-1831","authenticated-orcid":false,"given":"Shuaicheng","family":"Niu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4769-1526","authenticated-orcid":false,"given":"Jian","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00266"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00816"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00816"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"e_1_3_2_1_5_1","volume-title":"Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552","author":"DeVries Terrance","year":"2017","unstructured":"Terrance DeVries and Graham W Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_8_1","volume-title":"NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications.","author":"Francc","unstructured":"Francc ois Fleuret et al. 2021a. Test time adaptation through perturbation robustness. In NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications."},{"key":"e_1_3_2_1_9_1","volume-title":"NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications.","author":"Francc","unstructured":"Francc ois Fleuret et al. 2021b. Test time adaptation through perturbation robustness. In NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications."},{"key":"e_1_3_2_1_10_1","first-page":"29374","article-title":"Test-time training with masked autoencoders","volume":"35","author":"Gandelsman Yossi","year":"2022","unstructured":"Yossi Gandelsman, Yu Sun, Xinlei Chen, and Alexei Efros. 2022. Test-time training with masked autoencoders. In Advances in Neural Information Processing Systems, Vol. 35. 29374--29385.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","volume-title":"Heiko H Sch\u00fctt, Jonas Rauber, Matthias Bethge, and Felix A Wichmann.","author":"Geirhos Robert","year":"2017","unstructured":"Robert Geirhos, David HJ Janssen, Heiko H Sch\u00fctt, Jonas Rauber, Matthias Bethge, and Felix A Wichmann. 2017. Comparing deep neural networks against humans: object recognition when the signal gets weaker. arXiv preprint arXiv:1706.06969 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"e_1_3_2_1_13_1","volume-title":"Momentum Contrast for Unsupervised Visual Representation Learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"e_1_3_2_1_16_1","first-page":"2427","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","volume":"34","author":"Iwasawa Yusuke","year":"2021","unstructured":"Yusuke Iwasawa and Yutaka Matsuo. 2021a. Test-time classifier adjustment module for model-agnostic domain generalization. In Advances in Neural Information Processing Systems, Vol. 34. 2427--2440.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","first-page":"2427","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","volume":"34","author":"Iwasawa Yusuke","year":"2021","unstructured":"Yusuke Iwasawa and Yutaka Matsuo. 2021b. Test-time classifier adjustment module for model-agnostic domain generalization. In Advances in Neural Information Processing Systems, Vol. 34. 2427--2440.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18963--18974","author":"Fatih Kar Oug","year":"2022","unstructured":"Oug uzhan Fatih Kar, Teresa Yeo, Andrei Atanov, and Amir Zamir. 2022. 3d common corruptions and data augmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18963--18974."},{"key":"e_1_3_2_1_20_1","volume-title":"Sita: Single image test-time adaptation. arXiv preprint arXiv:2112.02355","author":"Khurana Ansh","year":"2021","unstructured":"Ansh Khurana, Sujoy Paul, Piyush Rai, Soma Biswas, and Gaurav Aggarwal. 2021. Sita: Single image test-time adaptation. arXiv preprint arXiv:2112.02355 (2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Exploring Temporally Dynamic Data Augmentation for Video Recognition. In The Eleventh International Conference on Learning Representations.","author":"Kim Taeoh","year":"2022","unstructured":"Taeoh Kim, Jinhyung Kim, Minho Shim, Sangdoo Yun, Myunggu Kang, Dongyoon Wee, and Sangyoun Lee. 2022. Exploring Temporally Dynamic Data Augmentation for Video Recognition. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66096-3_27"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00019"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_24"},{"key":"e_1_3_2_1_25_1","article-title":"Dynamic Hand Gesture Recognition Using Multi-direction 3D Convolutional Neural Networks","volume":"27","author":"Li Jie","year":"2019","unstructured":"Jie Li, Mingqiang Yang, Yupeng Liu, Yanyan Wang, Qinghe Zheng, and Deqiang Wang. 2019. Dynamic Hand Gesture Recognition Using Multi-direction 3D Convolutional Neural Networks. Engineering Letters, Vol. 27, 3 (2019).","journal-title":"Engineering Letters"},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. PMLR, 6028--6039","author":"Liang Jian","year":"2020","unstructured":"Jian Liang, Dapeng Hu, and Jiashi Feng. 2020a. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International Conference on Machine Learning. PMLR, 6028--6039."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning. PMLR, 6028--6039","author":"Liang Jian","year":"2020","unstructured":"Jian Liang, Dapeng Hu, and Jiashi Feng. 2020b. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International Conference on Machine Learning. PMLR, 6028--6039."},{"key":"e_1_3_2_1_28_1","volume-title":"TSM: Temporal Shift Module for Efficient Video Understanding. In IEEE\/CVF International Conference on Computer Vision. 7082--7092","author":"Lin Ji","year":"2019","unstructured":"Ji Lin, Chuang Gan, and Song Han. 2019. TSM: Temporal Shift Module for Efficient Video Understanding. In IEEE\/CVF International Conference on Computer Vision. 7082--7092."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02198"},{"key":"e_1_3_2_1_30_1","first-page":"21808","article-title":"TTT: When does self-supervised test-time training fail or thrive?","volume":"34","author":"Liu Yuejiang","year":"2021","unstructured":"Yuejiang Liu, Parth Kothari, Bastien Van Delft, Baptiste Bellot-Gurlet, Taylor Mordan, and Alexandre Alahi. 2021a. TTT: When does self-supervised test-time training fail or thrive?. In Advances in Neural Information Processing Systems, Vol. 34. 21808--21820.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01435"},{"key":"e_1_3_2_1_33_1","volume-title":"Evaluating prediction-time batch normalization for robustness under covariate shift. arXiv preprint arXiv:2006.10963","author":"Nado Zachary","year":"2020","unstructured":"Zachary Nado, Shreyas Padhy, D Sculley, Alexander D'Amour, Balaji Lakshminarayanan, and Jasper Snoek. 2020. Evaluating prediction-time batch normalization for robustness under covariate shift. arXiv preprint arXiv:2006.10963 (2020)."},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. PMLR, 16888--16905","author":"Niu Shuaicheng","year":"2022","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, and Mingkui Tan. 2022. Efficient test-time model adaptation without forgetting. In International Conference on Machine Learning. PMLR, 16888--16905."},{"key":"e_1_3_2_1_35_1","volume-title":"Towards Stable Test-time Adaptation in Dynamic Wild World. In The Eleventh International Conference on Learning Representations.","author":"Niu Shuaicheng","year":"2023","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Zhiquan Wen, Yaofo Chen, Peilin Zhao, and Mingkui Tan. 2023. Towards Stable Test-time Adaptation in Dynamic Wild World. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01412"},{"key":"e_1_3_2_1_37_1","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume":"33","author":"Schneider Steffen","year":"2020","unstructured":"Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann, Wieland Brendel, and Matthias Bethge. 2020. Improving robustness against common corruptions by covariate shift adaptation. In Advances in Neural Information Processing Systems, Vol. 33. 11539--11551.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"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","unstructured":"Yongyi Su Xun Xu and Kui Jia. 2022. Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_41_1","volume-title":"International conference on machine learning. PMLR, 9229--9248","author":"Sun Yu","year":"2020","unstructured":"Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei Efros, and Moritz Hardt. 2020. Test-time training with self-supervision for generalization under distribution shifts. In International conference on machine learning. PMLR, 9229--9248."},{"key":"e_1_3_2_1_42_1","volume-title":"On-target adaptation. arXiv preprint arXiv:2109.01087","author":"Wang Dequan","year":"2021","unstructured":"Dequan Wang, Shaoteng Liu, Sayna Ebrahimi, Evan Shelhamer, and Trevor Darrell. 2021b. On-target adaptation. arXiv preprint arXiv:2109.01087 (2021)."},{"key":"e_1_3_2_1_43_1","volume-title":"International Conference on Learning Representations.","author":"Wang Dequan","year":"2021","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2021c. Tent: Fully test-time adaptation by entropy minimization. International Conference on Learning Representations."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Xie Cihang","unstructured":"Cihang Xie, Yuxin Wu, Laurens van der Maaten, Alan L. Yuille, and Kaiming He. 2019. Feature Denoising for Improving Adversarial Robustness. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_9"},{"key":"e_1_3_2_1_47_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Yi Chenyu","year":"2021","unstructured":"Chenyu Yi, Siyuan Yang, Haoliang Li, Yap-peng Tan, and Alex Kot. 2021. Benchmarking the robustness of spatial-temporal models against corruptions. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_1_49_1","volume-title":"Byeongho Heo, Dongyoon Han, and Jinhyung Kim.","author":"Yun Sangdoo","year":"2020","unstructured":"Sangdoo Yun, Seong Joon Oh, Byeongho Heo, Dongyoon Han, and Jinhyung Kim. 2020. Videomix: Rethinking data augmentation for video classification. arXiv preprint arXiv:2012.03457 (2020)."},{"key":"e_1_3_2_1_50_1","volume-title":"International Conference on Learning Representations.","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2018. mixup: Beyond empirical risk minimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_51_1","first-page":"38629","article-title":"Memo: Test time robustness via adaptation and augmentation","volume":"35","author":"Zhang Marvin","year":"2022","unstructured":"Marvin Zhang, Sergey Levine, and Chelsea Finn. 2022. Memo: Test time robustness via adaptation and augmentation. In Advances in Neural Information Processing Systems, Vol. 35. 38629--38642.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414003"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7008"}],"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\/3581783.3612153","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:04:35Z","timestamp":1755821075000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":53,"alternative-id":["10.1145\/3581783.3612153","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612153","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"}}]}}