{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:56:16Z","timestamp":1777568176393,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":367,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-1930041, CMMI-2038215"],"award-info":[{"award-number":["CNS-1930041, CMMI-2038215"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National AI Institute for Edge Computing Leveraging Next Generation Wireless Networks","award":["2112562"],"award-info":[{"award-number":["2112562"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611835","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"5796-5806","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["VPA: Fully Test-Time Visual Prompt Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1170-4735","authenticated-orcid":false,"given":"Jiachen","family":"Sun","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2135-7476","authenticated-orcid":false,"given":"Mark","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"Meta AI, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0509-1654","authenticated-orcid":false,"given":"Melissa","family":"Hall","sequence":"additional","affiliation":[{"name":"Meta AI, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7763-4263","authenticated-orcid":false,"given":"Ivan","family":"Evtimov","sequence":"additional","affiliation":[{"name":"Meta AI, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9844-2055","authenticated-orcid":false,"given":"Z. Morley","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3189-5498","authenticated-orcid":false,"given":"Cristian Canton","family":"Ferrer","sequence":"additional","affiliation":[{"name":"Meta AI, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1980-5768","authenticated-orcid":false,"given":"Caner","family":"Hazirbas","sequence":"additional","affiliation":[{"name":"Meta AI, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. Machine learning inference during deployment. https: \/\/learn.microsoft.com\/en-us\/azure\/cloud-adoption-framework\/innovate\/best- practices\/ml-deployment-inference#batch-inference."},{"key":"e_1_3_2_1_2_1","unstructured":"2022. Random Cropping in Pytorch. https:\/\/pytorch.org\/vision\/main\/generated\/ torchvision.transforms.RandomCrop.html."},{"key":"e_1_3_2_1_3_1","volume-title":"Exploring visual prompts for adapting large-scale models. arXiv preprint arXiv:2203.17274","author":"Bahng Hyojin","year":"2022","unstructured":"Hyojin Bahng, Ali Jahanian, Swami Sankaranarayanan, and Phillip Isola. 2022. Exploring visual prompts for adapting large-scale models. arXiv preprint arXiv:2203.17274, Vol. 1, 3 (2022), 4."},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d Alch\u00e9-Buc","author":"Barbu Andrei","year":"2019","unstructured":"Andrei Barbu, David Mayo, Julian Alverio, William Luo, Christopher Wang, Dan Gutfreund, Josh Tenenbaum, and Boris Katz. 2019. ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/97af07a14cacba681feacf3012730892-Paper.pdf"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Dhamija Akshay Raj","year":"2018","unstructured":"Akshay Raj Dhamija, Manuel G\u00fcnther, and Terrance Boult. 2018. Reducing network agnostophobia. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_12_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Christopher KI Williams, and Bernhard Sch\u00f6lkopf","author":"Eastwood Cian","year":"2021","unstructured":"Cian Eastwood, Ian Mason, Christopher KI Williams, and Bernhard Sch\u00f6lkopf. 2021. Source-free adaptation to measurement shift via bottom-up feature restoration. arXiv preprint arXiv:2107.05446 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Adversarial reprogramming of neural networks. arXiv preprint arXiv:1806.11146","author":"Elsayed Gamaleldin F","year":"2018","unstructured":"Gamaleldin F Elsayed, Ian Goodfellow, and Jascha Sohl-Dickstein. 2018. Adversarial reprogramming of neural networks. arXiv preprint arXiv:1806.11146 (2018)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25922"},{"key":"e_1_3_2_1_16_1","volume-title":"Back to the Source: Diffusion-Driven Test-Time Adaptation. arXiv preprint arXiv:2207.03442","author":"Gao Jin","year":"2022","unstructured":"Jin Gao, Jialing Zhang, Xihui Liu, Trevor Darrell, Evan Shelhamer, and Dequan Wang. 2022b. Back to the Source: Diffusion-Driven Test-Time Adaptation. arXiv preprint arXiv:2207.03442 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Visual Prompt Tuning for Test-time Domain Adaptation. arXiv preprint arXiv:2210.04831","author":"Gao Yunhe","year":"2022","unstructured":"Yunhe Gao, Xingjian Shi, Yi Zhu, Hao Wang, Zhiqiang Tang, Xiong Zhou, Mu Li, and Dimitris N Metaxas. 2022a. Visual Prompt Tuning for Test-time Domain Adaptation. arXiv preprint arXiv:2210.04831 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Test-time adaptation via conjugate pseudo-labels. arXiv preprint arXiv:2207.09640","author":"Goyal Sachin","year":"2022","unstructured":"Sachin Goyal, Mingjie Sun, Aditi Raghunathan, and Zico Kolter. 2022. Test-time adaptation via conjugate pseudo-labels. arXiv preprint arXiv:2207.09640 (2022)."},{"key":"e_1_3_2_1_19_1","volume-title":"Ppt: Pre-trained prompt tuning for few-shot learning. arXiv preprint arXiv:2109.04332","author":"Gu Yuxian","year":"2021","unstructured":"Yuxian Gu, Xu Han, Zhiyuan Liu, and Minlie Huang. 2021. Ppt: Pre-trained prompt tuning for few-shot learning. arXiv preprint arXiv:2109.04332 (2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"Ptr: Prompt tuning with rules for text classification. arXiv preprint arXiv:2105.11259","author":"Han Xu","year":"2021","unstructured":"Xu Han, Weilin Zhao, Ning Ding, Zhiyuan Liu, and Maosong Sun. 2021. Ptr: Prompt tuning with rules for text classification. arXiv preprint arXiv:2105.11259 (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_23_1","volume-title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization. ICCV","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, and Justin Gilmer. 2021a. The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization. ICCV (2021)."},{"key":"e_1_3_2_1_24_1","volume-title":"Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks and Thomas Dietterich. 2019. Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks, Norman Mu, Ekin D Cubuk, Barret Zoph, Justin Gilmer, and Balaji Lakshminarayanan. 2019. Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR, 448--456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. PMLR, 448--456."},{"key":"e_1_3_2_1_28_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. 2021. Test-time classifier adjustment module for model-agnostic domain generalization. Advances in Neural Information Processing Systems, Vol. 34 (2021), 2427--2440.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"Visual prompt tuning. arXiv preprint arXiv:2203.12119","author":"Jia Menglin","year":"2022","unstructured":"Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge Belongie, Bharath Hariharan, and Ser-Nam Lim. 2022. Visual prompt tuning. arXiv preprint arXiv:2203.12119 (2022)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3110179"},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning. PMLR, 5637--5664","author":"Koh Pang Wei","year":"2021","unstructured":"Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, et al. 2021. Wilds: A benchmark of in-the-wild distribution shifts. In International Conference on Machine Learning. PMLR, 5637--5664."},{"key":"e_1_3_2_1_32_1","volume-title":"Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment. arXiv preprint arXiv:2206.13951","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment. arXiv preprint arXiv:2206.13951 (2022)."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 1378--1387","author":"Kumar Ankit","year":"2016","unstructured":"Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, and Richard Socher. 2016. Ask me anything: Dynamic memory networks for natural language processing. In International conference on machine learning. PMLR, 1378--1387."},{"key":"e_1_3_2_1_34_1","volume-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv preprint arXiv:2202.10054","author":"Kumar Ananya","year":"2022","unstructured":"Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, and Percy Liang. 2022. Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv preprint arXiv:2202.10054 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4544--4553","author":"Kundu Jogendra Nath","year":"2020","unstructured":"Jogendra Nath Kundu, Naveen Venkat, R Venkatesh Babu, et al. 2020. Universal source-free domain adaptation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4544--4553."},{"key":"e_1_3_2_1_36_1","unstructured":"Yann LeCun Yoshua Bengio et al. 1995. Convolutional networks for images speech and time series. The handbook of brain theory and neural networks Vol. 3361 10 (1995) 1995."},{"key":"e_1_3_2_1_37_1","volume-title":"Deep learning. nature","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature, Vol. 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_38_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_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00966"},{"key":"e_1_3_2_1_40_1","volume-title":"International Conference on Machine Learning. PMLR, 6028--6039","author":"Liang Jian","year":"2020","unstructured":"Jian Liang, Dapeng Hu, and Jiashi Feng. 2020. 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_41_1","volume-title":"prompt, and predict: A systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586","author":"Liu Pengfei","year":"2021","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2021. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586 (2021)."},{"key":"e_1_3_2_1_42_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_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"e_1_3_2_1_44_1","volume-title":"Visda: The visual domain adaptation challenge. arXiv preprint arXiv:1710.06924","author":"Peng Xingchao","year":"2017","unstructured":"Xingchao Peng, Ben Usman, Neela Kaushik, Judy Hoffman, Dequan Wang, and Kate Saenko. 2017. Visda: The visual domain adaptation challenge. arXiv preprint arXiv:1710.06924 (2017)."},{"key":"e_1_3_2_1_45_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_1_46_1","volume-title":"International Conference on Machine Learning. PMLR, 5389--5400","author":"Recht Benjamin","year":"2019","unstructured":"Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, and Vaishaal Shankar. 2019. Do imagenet classifiers generalize to imagenet?. In International Conference on Machine Learning. PMLR, 5389--5400."},{"key":"e_1_3_2_1_47_1","volume-title":"An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747","author":"Ruder Sebastian","year":"2016","unstructured":"Sebastian Ruder. 2016. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)."},{"key":"e_1_3_2_1_48_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. Advances in Neural Information Processing Systems, Vol. 33 (2020), 11539--11551.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","volume-title":"Test-time prompt tuning for zero-shot generalization in vision-language models. arXiv preprint arXiv:2209.07511","author":"Shu Manli","year":"2022","unstructured":"Manli Shu, Weili Nie, De-An Huang, Zhiding Yu, Tom Goldstein, Anima Anandkumar, and Chaowei Xiao. 2022. Test-time prompt tuning for zero-shot generalization in vision-language models. arXiv preprint arXiv:2209.07511 (2022)."},{"key":"e_1_3_2_1_50_1","volume-title":"Alexey Kurakin, and Chun-Liang Li.","author":"Sohn Kihyuk","year":"2020","unstructured":"Kihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang, Han Zhang, Colin A Raffel, Ekin Dogus Cubuk, Alexey Kurakin, and Chun-Liang Li. 2020. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, Vol. 33 (2020), 596--608."},{"key":"e_1_3_2_1_51_1","volume-title":"Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures. In 29th USENIX Security Symposium (USENIX Security 20)","author":"Sun Jiachen","unstructured":"Jiachen Sun, Yulong Cao, Qi Alfred Chen, and Z. Morley Mao. 2020a. Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures. In 29th USENIX Security Symposium (USENIX Security 20). USENIX Association, 877--894. https:\/\/www.usenix.org\/conference\/usenixsecurity20\/presentation\/sun"},{"key":"e_1_3_2_1_52_1","first-page":"15498","article-title":"Adversarially robust 3d point cloud recognition using self-supervisions","volume":"34","author":"Sun Jiachen","year":"2021","unstructured":"Jiachen Sun, Yulong Cao, Christopher B Choy, Zhiding Yu, Anima Anandkumar, Zhuoqing Morley Mao, and Chaowei Xiao. 2021. Adversarially robust 3d point cloud recognition using self-supervisions. Advances in Neural Information Processing Systems, Vol. 34 (2021), 15498--15512.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_53_1","volume-title":"Qi Alfred Chen, and Z Morley Mao","author":"Sun Jiachen","year":"2020","unstructured":"Jiachen Sun, Karl Koenig, Yulong Cao, Qi Alfred Chen, and Z Morley Mao. 2020b. On adversarial robustness of 3d point cloud classification under adaptive attacks. arXiv preprint arXiv:2011.11922 (2020)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_38"},{"key":"e_1_3_2_1_55_1","volume-title":"Pointdp: Diffusion-driven purification against adversarial attacks on 3d point cloud recognition. arXiv preprint arXiv:2208.09801","author":"Sun Jiachen","year":"2022","unstructured":"Jiachen Sun, Weili Nie, Zhiding Yu, Z Morley Mao, and Chaowei Xiao. 2022b. Pointdp: Diffusion-driven purification against adversarial attacks on 3d point cloud recognition. arXiv preprint arXiv:2208.09801 (2022)."},{"key":"e_1_3_2_1_56_1","volume-title":"Benchmarking robustness of 3d point cloud recognition against common corruptions. arXiv preprint arXiv:2201.12296","author":"Sun Jiachen","year":"2022","unstructured":"Jiachen Sun, Qingzhao Zhang, Bhavya Kailkhura, Zhiding Yu, Chaowei Xiao, and Z Morley Mao. 2022c. Benchmarking robustness of 3d point cloud recognition against common corruptions. arXiv preprint arXiv:2201.12296 (2022)."},{"key":"e_1_3_2_1_57_1","volume-title":"CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception. arXiv preprint arXiv:2306.00349","author":"Sun Jiachen","year":"2023","unstructured":"Jiachen Sun, Haizhong Zheng, Qingzhao Zhang, Atul Prakash, Z Morley Mao, and Chaowei Xiao. 2023. CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception. arXiv preprint arXiv:2306.00349 (2023)."},{"key":"e_1_3_2_1_58_1","unstructured":"Yu Sun Xiaolong Wang Zhuang Liu John Miller Alexei A Efros and Moritz Hardt. 2019. Test-time training for out-of-distribution generalization. (2019)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092646"},{"key":"e_1_3_2_1_60_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_61_1","volume-title":"Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726","author":"Wang Dequan","year":"2020","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2020. Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"e_1_3_2_1_63_1","volume-title":"Memo: Test time robustness via adaptation and augmentation. arXiv preprint arXiv:2110.09506","author":"Zhang Marvin","year":"2021","unstructured":"Marvin Zhang, Sergey Levine, and Chelsea Finn. 2021. Memo: Test time robustness via adaptation and augmentation. arXiv preprint arXiv:2110.09506 (2021)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01473"},{"key":"e_1_3_2_1_65_1","volume-title":"ibot: Image bert pre-training with online tokenizer. arXiv preprint arXiv:2111.07832","author":"Zhou Jinghao","year":"2021","unstructured":"Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, and Tao Kong. 2021. ibot: Image bert pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"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\/3581783.3611835","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611835","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:58:00Z","timestamp":1755820680000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":68,"alternative-id":["10.1145\/3581783.3611835","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611835","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"}}]}}