@inproceedings{bb154800,
        AUTHOR = "Tu, Z.Z. and Talebi, H. and Zhang, H. and Yang, F. and Milanfar, P. and Bovik, A. and Li, Y.X.",
        TITLE = "MAXIM: Multi-Axis MLP for Image Processing",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "5759-5770",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150718"}

@inproceedings{bb154801,
        AUTHOR = "Hou, Z.J. and Kung, S.Y.",
        TITLE = "Multi-Dimensional Vision Transformer Compression via Dependency
Guided Gaussian Process Search",
        BOOKTITLE = EVW22,
        YEAR = "2022",
        PAGES = "3668-3677",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150719"}

@inproceedings{bb154802,
        AUTHOR = "Zhang, J.N. and Peng, H.W. and Wu, K. and Liu, M.C. and Xiao, B. and Fu, J.L. and Yuan, L.",
        TITLE = "MiniViT: Compressing Vision Transformers with Weight Multiplexing",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12135-12144",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150720"}

@inproceedings{bb154803,
        AUTHOR = "Chen, T.L. and Zhang, Z.Y. and Cheng, Y. and Awadallah, A. and Wang, Z.Y.",
        TITLE = "The Principle of Diversity: Training Stronger Vision Transformers
Calls for Reducing All Levels of Redundancy",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12010-12020",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150721"}

@inproceedings{bb154804,
        AUTHOR = "Lu, J.H. and Zhang, X.S. and Zhao, T.L. and He, X.Y. and Cheng, J.",
        TITLE = "APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "10041-10050",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150722"}

@inproceedings{bb154805,
        AUTHOR = "Hatamizadeh, A. and Yin, H.X. and Roth, H. and Li, W.Q. and Kautz, J. and Xu, D. and Molchanov, P.",
        TITLE = "GradViT: Gradient Inversion of Vision Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "10011-10020",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150723"}

@inproceedings{bb154806,
        AUTHOR = "Zhang, H.F. and Duan, J.R. and Xue, M.Q. and Song, J. and Sun, L. and Song, M.L.",
        TITLE = "Bootstrapping ViTs: Towards Liberating Vision Transformers from
Pre-training",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "8934-8943",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150724"}

@inproceedings{bb154807,
        AUTHOR = "Chavan, A. and Shen, Z.Q. and Liu, Z. and Liu, Z. and Cheng, K.T. and Xing, E.",
        TITLE = "Vision Transformer Slimming:
Multi-Dimension Searching in Continuous Optimization Space",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "4921-4931",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150725"}

@inproceedings{bb154808,
        AUTHOR = "Chen, R.J. and Chen, C.K. and Li, Y.C. and Chen, T.Y. and Trister, A.D. and Krishnan, R.G. and Mahmood, F.",
        TITLE = "Scaling Vision Transformers to Gigapixel Images via Hierarchical
Self-Supervised Learning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "16123-16134",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150726"}

@inproceedings{bb154809,
        AUTHOR = "Zhai, X.H. and Kolesnikov, A. and Houlsby, N. and Beyer, L.",
        TITLE = "Scaling Vision Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "1204-1213",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150727"}

@inproceedings{bb154810,
        AUTHOR = "Meng, L.C. and Li, H.D. and Chen, B.C. and Lan, S.Y. and Wu, Z.X. and Jiang, Y.G. and Lim, S.N.",
        TITLE = "AdaViT: Adaptive Vision Transformers for Efficient Image Recognition",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12299-12308",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150728"}

@inproceedings{bb154811,
        AUTHOR = "Herrmann, C. and Sargent, K. and Jiang, L. and Zabih, R. and Chang, H. and Liu, C. and Krishnan, D. and Sun, D.Q.",
        TITLE = "Pyramid Adversarial Training Improves ViT Performance",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "13409-13419",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150729"}

@inproceedings{bb154812,
        AUTHOR = "Li, C.L. and Zhuang, B. and Wang, G.R. and Liang, X.D. and Chang, X.J. and Yang, Y.",
        TITLE = "Automated Progressive Learning for Efficient Training of Vision
Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12476-12486",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150730"}

@inproceedings{bb154813,
        AUTHOR = "Pu, M.Y. and Huang, Y.P. and Liu, Y.M. and Guan, Q.J. and Ling, H.B.",
        TITLE = "EDTER: Edge Detection with Transformer",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "1392-1402",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150731"}

@inproceedings{bb154814,
        AUTHOR = "Zhu, R. and Li, Z.Q. and Matai, J. and Porikli, F.M. and Chandraker, M.",
        TITLE = "IRISformer: Dense Vision Transformers for Single-Image Inverse
Rendering in Indoor Scenes",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "2812-2821",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150732"}

@inproceedings{bb154815,
        AUTHOR = "Ermolov, A. and Mirvakhabova, L. and Khrulkov, V. and Sebe, N. and Oseledets, I.",
        TITLE = "Hyperbolic Vision Transformers: Combining Improvements in Metric
Learning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "7399-7409",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150733"}

@inproceedings{bb154816,
        AUTHOR = "Zhang, C.Z. and Zhang, M.Y. and Zhang, S.H. and Jin, D.S. and Zhou, Q. and Cai, Z.A. and Zhao, H. and Liu, X.L. and Liu, Z.W.",
        TITLE = "Delving Deep into the Generalization of Vision Transformers under
Distribution Shifts",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "7267-7276",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150734"}

@inproceedings{bb154817,
        AUTHOR = "Hou, Z. and Yu, B. and Tao, D.C.",
        TITLE = "BatchFormer: Learning to Explore Sample Relationships for Robust
Representation Learning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "7246-7256",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150735"}

@inproceedings{bb154818,
        AUTHOR = "Zamir, S.W. and Arora, A. and Khan, S. and Hayat, M. and Khan, F.S. and Yang, M.H.",
        TITLE = "Restormer: Efficient Transformer for High-Resolution Image
Restoration",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "5718-5729",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150736"}

@inproceedings{bb154819,
        AUTHOR = "Lin, K. and Wang, L.J. and Liu, Z.C.",
        TITLE = "Mesh Graphormer",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "12919-12928",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150737"}

@inproceedings{bb154820,
        AUTHOR = "Casey, E. and Perez, V. and Li, Z.R.",
        TITLE = "The Animation Transformer: Visual Correspondence via Segment Matching",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "11303-11312",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150738"}

@inproceedings{bb154821,
        AUTHOR = "Reizenstein, J. and Shapovalov, R. and Henzler, P. and Sbordone, L. and Labatut, P. and Novotny, D.",
        TITLE = "Common Objects in 3D: Large-Scale Learning and Evaluation of
Real-life 3D Category Reconstruction",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "10881-10891",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150739"}

@inproceedings{bb154822,
        AUTHOR = "Wu, H.P. and Xiao, B. and Codella, N. and Liu, M.C. and Dai, X.Y. and Yuan, L. and Zhang, L.",
        TITLE = "CvT: Introducing Convolutions to Vision Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "22-31",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150740"}

@inproceedings{bb154823,
        AUTHOR = "Touvron, H. and Cord, M. and Sablayrolles, A. and Synnaeve, G. and Jegou, H.",
        TITLE = "Going deeper with Image Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "32-42",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150741"}

@inproceedings{bb154824,
        AUTHOR = "Zhao, J.W. and Yan, K. and Zhao, Y.F. and Guo, X.W. and Huang, F.Y. and Li, J.",
        TITLE = "Transformer-based Dual Relation Graph for Multi-label Image
Recognition",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "163-172",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150742"}

@inproceedings{bb154825,
        AUTHOR = "Pan, Z.Z. and Zhuang, B. and Liu, J. and He, H.Y. and Cai, J.F.",
        TITLE = "Scalable Vision Transformers with Hierarchical Pooling",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "367-376",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150743"}

@inproceedings{bb154826,
        AUTHOR = "Wu, B. and Xu, C.F. and Dai, X.L. and Wan, A. and Zhang, P.Z. and Yan, Z.C. and Tomizuka, M. and Gonzalez, J. and Keutzer, K. and Vajda, P.",
        TITLE = "Visual Transformers: Where Do Transformers Really Belong in Vision
Models?",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "579-589",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150744"}

@inproceedings{bb154827,
        AUTHOR = "Qiu, Y. and Yamamoto, S. and Nakashima, K. and Suzuki, R. and Iwata, K. and Kataoka, H. and Satoh, Y.",
        TITLE = "Describing and Localizing Multiple Changes with Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1951-1960",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150745"}

@inproceedings{bb154828,
        AUTHOR = "Song, M. and Choi, J. and Han, B.H.",
        TITLE = "Variable-Rate Deep Image Compression through Spatially-Adaptive
Feature Transform",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2360-2369",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150746"}

@inproceedings{bb154829,
        AUTHOR = "Dong, Q. and Tu, Z.W. and Liao, H.F. and Zhang, Y.T. and Mahadevan, V. and Soatto, S.",
        TITLE = "Visual Relationship Detection Using Part-and-Sum Transformers with
Composite Queries",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "3530-3539",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150747"}

@inproceedings{bb154830,
        AUTHOR = "Fan, H.Q. and Xiong, B. and Mangalam, K. and Li, Y.H. and Yan, Z.C. and Malik, J. and Feichtenhofer, C.",
        TITLE = "Multiscale Vision Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "6804-6815",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150748"}

@inproceedings{bb154831,
        AUTHOR = "Mahmood, K. and Mahmood, R. and van Dijk, M.",
        TITLE = "On the Robustness of Vision Transformers to Adversarial Examples",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "7818-7827",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150749"}

@inproceedings{bb154832,
        AUTHOR = "Chen, X.L. and Xie, S. and He, K.",
        TITLE = "An Empirical Study of Training Self-Supervised Vision Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "9620-9629",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150750"}

@inproceedings{bb154833,
        AUTHOR = "Yuan, Y. and Weng, X. and Ou, Y. and Kitani, K.",
        TITLE = "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent
Forecasting",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "9793-9803",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150751"}

@inproceedings{bb154834,
        AUTHOR = "Wu, K. and Peng, H.W. and Chen, M.H. and Fu, J.L. and Chao, H.Y.",
        TITLE = "Rethinking and Improving Relative Position Encoding for Vision
Transformer",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "10013-10021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150752"}

@inproceedings{bb154835,
        AUTHOR = "Bhojanapalli, S. and Chakrabarti, A. and Glasner, D. and Li, D. and Unterthiner, T. and Veit, A.",
        TITLE = "Understanding Robustness of Transformers for Image Classification",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "10211-10221",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150753"}

@inproceedings{bb154836,
        AUTHOR = "Yan, B. and Peng, H. and Fu, J.L. and Wang, D. and Lu, H.C.",
        TITLE = "Learning Spatio-Temporal Transformer for Visual Tracking",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "10428-10437",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150754"}

@inproceedings{bb154837,
        AUTHOR = "Voskou, A. and Panousis, K.P. and Kosmopoulos, D. and Metaxas, D.N. and Chatzis, S.",
        TITLE = "Stochastic Transformer Networks with Linear Competing Units:
Application to end-to-end SL Translation",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "11926-11935",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150755"}

@inproceedings{bb154838,
        AUTHOR = "Ranftl, R. and Bochkovskiy, A. and Koltun, V.",
        TITLE = "Vision Transformers for Dense Prediction",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "12159-12168",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150756"}

@inproceedings{bb154839,
        AUTHOR = "Chen, M.H. and Peng, H.W. and Fu, J.L. and Ling, H.B.",
        TITLE = "AutoFormer: Searching Transformers for Visual Recognition",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "12250-12260",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150757"}

@inproceedings{bb154840,
        AUTHOR = "Yuan, K. and Guo, S.P. and Liu, Z.W. and Zhou, A. and Yu, F.W. and Wu, W.",
        TITLE = "Incorporating Convolution Designs into Visual Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "559-568",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150758"}

@inproceedings{bb154841,
        AUTHOR = "Chen, Z. and Xie, L.X. and Niu, J.W. and Liu, X.F. and Wei, L.H. and Tian, Q.",
        TITLE = "Visformer: The Vision-friendly Transformer",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "569-578",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150759"}

@inproceedings{bb154842,
        AUTHOR = "Yao, Z.L. and Cao, Y. and Lin, Y.T. and Liu, Z. and Zhang, Z. and Hu, H.",
        TITLE = "Leveraging Batch Normalization for Vision Transformers",
        BOOKTITLE = NeruArch21,
        YEAR = "2021",
        PAGES = "413-422",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150760"}

@inproceedings{bb154843,
        AUTHOR = "Graham, B. and El Nouby, A. and Touvron, H. and Stock, P. and Joulin, A. and Jegou, H. and Douze, M.",
        TITLE = "LeViT: a Vision Transformer in ConvNet's Clothing for Faster
Inference",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "12239-12249",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150761"}

@inproceedings{bb154844,
        AUTHOR = "Horvath, J. and Baireddy, S. and Hao, H.X. and Montserrat, D.M. and Delp, E.J.",
        TITLE = "Manipulation Detection in Satellite Images Using Vision Transformer",
        BOOKTITLE = WMF21,
        YEAR = "2021",
        PAGES = "1032-1041",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150762"}

@inproceedings{bb154845,
        AUTHOR = "Horvath, J. and Montserrat, D.M. and Hao, H.X. and Delp, E.J.",
        TITLE = "Manipulation Detection in Satellite Images Using Deep Belief Networks",
        BOOKTITLE = WMF20,
        YEAR = "2020",
        PAGES = "2832-2840",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150763"}

@inproceedings{bb154846,
        AUTHOR = "Beal, J. and Wu, H.Y. and Park, D.H. and Zhai, A. and Kislyuk, D.",
        TITLE = "Billion-Scale Pretraining with Vision Transformers for Multi-Task
Visual Representations",
        BOOKTITLE = WACV22,
        YEAR = "2022",
        PAGES = "1431-1440",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT150764"}

@article{bb154847,
        AUTHOR = "Jiang, B. and Zhao, K.K. and Tang, J.",
        TITLE = "RGTransformer: Region-Graph Transformer for Image Representation and
Few-Shot Classification",
        JOURNAL = SPLetters,
        VOLUME = "29",
        YEAR = "2022",
        PAGES = "792-796",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150765"}

@article{bb154848,
        AUTHOR = "Kim, B. and Kim, J. and Ye, J.C.",
        TITLE = "Task-Agnostic Vision Transformer for Distributed Learning of Image
Processing",
        JOURNAL = IP,
        VOLUME = "32",
        YEAR = "2023",
        PAGES = "203-218",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150766"}

@article{bb154849,
        AUTHOR = "Park, S. and Ye, J.C.",
        TITLE = "Multi-Task Distributed Learning Using Vision Transformer With Random
Patch Permutation",
        JOURNAL = MedImg,
        VOLUME = "42",
        YEAR = "2023",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "2091-2105",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150767"}

@article{bb154850,
        AUTHOR = "Kim, B.J. and Choi, H. and Jang, H. and Lee, D.G. and Jeong, W. and Kim, S.W.",
        TITLE = "Improved robustness of vision transformers via prelayernorm in patch
embedding",
        JOURNAL = PR,
        VOLUME = "141",
        YEAR = "2023",
        PAGES = "109659",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150768"}

@article{bb154851,
        AUTHOR = "Zhou, D. and Hou, Q. and Yang, L.J. and Jin, X.J. and Feng, J.S.",
        TITLE = "Token Selection is a Simple Booster for Vision Transformers",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "12738-12746",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150769"}

@article{bb154852,
        AUTHOR = "Feng, Z.Z. and Zhang, S.L.",
        TITLE = "Efficient Vision Transformer via Token Merger",
        JOURNAL = IP,
        VOLUME = "32",
        YEAR = "2023",
        PAGES = "4156-4169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150770"}

@article{bb154853,
        AUTHOR = "Qian, S.J. and Zhu, Y. and Li, W.B. and Li, M. and Jia, J.Y.",
        TITLE = "What Makes for Good Tokenizers in Vision Transformer?",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "13011-13023",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150771"}

@article{bb154854,
        AUTHOR = "Fu, K. and Yuan, M.Z. and Liu, S.L. and Wang, M.",
        TITLE = "Boosting Point-BERT by Multi-Choice Tokens",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "438-447",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150772"}

@article{bb154855,
        AUTHOR = "Yan, F.Y. and Yan, B. and Liang, W. and Pei, M.T.",
        TITLE = "Token labeling-guided multi-scale medical image classification",
        JOURNAL = PRL,
        VOLUME = "178",
        YEAR = "2024",
        PAGES = "28-34",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150773"}

@article{bb154856,
        AUTHOR = "Li, Y.X. and Huang, Y.W. and He, N. and Ma, K. and Zheng, Y.F.",
        TITLE = "Improving vision transformer for medical image classification via
token-wise perturbation",
        JOURNAL = JVCIR,
        VOLUME = "98",
        YEAR = "2024",
        PAGES = "104022",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150774"}

@article{bb154857,
        AUTHOR = "Kang, J.Y. and Heo, B. and Choe, J.",
        TITLE = "Improving ViT interpretability with patch-level mask prediction",
        JOURNAL = PRL,
        VOLUME = "187",
        YEAR = "2025",
        PAGES = "73-79",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150775"}

@article{bb154858,
        AUTHOR = "Arya, R.K. and Peddi, R. and Srivastava, R.",
        TITLE = "Hyperspectral image classification using hybrid convolutional-based
cross-patch retentive network",
        JOURNAL = CVIU,
        VOLUME = "257",
        YEAR = "2025",
        PAGES = "104382",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150776"}

@article{bb154859,
        AUTHOR = "Niu, Y. and Song, Z.C. and Luo, Q.Y. and Chen, G.C. and Ma, M.M. and Li, F.",
        TITLE = "ATMformer: An Adaptive Token Merging Vision Transformer for Remote
Sensing Image Scene Classification",
        JOURNAL = RS,
        VOLUME = "17",
        YEAR = "2025",
        NUMBER = "4",
        PAGES = "660",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150777"}

@article{bb154860,
        AUTHOR = "Wang, Y.C. and Yang, Y.Z.",
        TITLE = "Efficient Visual Transformer by Learnable Token Merging",
        JOURNAL = PAMI,
        VOLUME = "47",
        YEAR = "2025",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "9597-9608",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150778"}

@inproceedings{bb154861,
        AUTHOR = "Bergner, B. and Lippert, C. and Mahendran, A.",
        TITLE = "Token Cropr: Faster ViTs for Quite a Few Tasks",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "9740-9750",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150779"}

@inproceedings{bb154862,
        AUTHOR = "Dang, C.X. and Duan, Z. and An, P. and Zhang, X.M. and Hu, X. and Ma, J.",
        TITLE = "FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term
3D Object Detection",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "17029-17038",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150780"}

@inproceedings{bb154863,
        AUTHOR = "Olszewski, J. and Rymarczyk, D. and Wojcik, P. and Pach, M. and Zielinski, B.",
        TITLE = "TORE: Token Recycling in Vision Transformers for Efficient Active
Visual Exploration",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "8606-8616",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150781"}

@inproceedings{bb154864,
        AUTHOR = "Eliopoulos, N.J. and Jajal, P. and Davis, J.C. and Liu, G. and Thiravathukal, G.K. and Lu, Y.H.",
        TITLE = "Pruning One More Token is Enough: Leveraging Latency-Workload
Non-Linearities for Vision Transformers on the Edge",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "7153-7162",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150782"}

@inproceedings{bb154865,
        AUTHOR = "Koner, R. and Jain, G. and Jain, P. and Tresp, V. and Paul, S.",
        TITLE = "LookupVIT: Compressing Visual Information to a Limited Number of Tokens",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "LXXXVI: 322-337",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150783"}

@inproceedings{bb154866,
        AUTHOR = "Jie, S. and Tang, Y.H. and Guo, J.Y. and Deng, Z.H. and Han, K. and Wang, Y.H.",
        TITLE = "Token Compensator: Altering Inference Cost of Vision Transformer
Without Re-tuning",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XVI: 76-94",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150784"}

@inproceedings{bb154867,
        AUTHOR = "Huang, W.X. and Shen, Y.H. and Xie, J. and Zhang, B.C. and He, G.Q. and Li, K. and Sun, X. and Lin, S.H.",
        TITLE = "A General and Efficient Training for Transformer via Token Expansion",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "15783-15792",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150785"}

@inproceedings{bb154868,
        AUTHOR = "Wu, J. and Duan, B. and Kang, W.T. and Tang, H. and Yan, Y.",
        TITLE = "Token Transformation Matters: Towards Faithful Post-Hoc Explanation
for Vision Transformer",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "10926-10935",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150786"}

@inproceedings{bb154869,
        AUTHOR = "Yu, Q. and Tanaka, M. and Fujiwara, K.",
        TITLE = "Exploring Vision Transformers for 3D Human Motion-Language Models
with Motion Patches",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "937-946",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150787"}

@inproceedings{bb154870,
        AUTHOR = "Yuan, X. and Fei, H.L. and Baek, J.",
        TITLE = "Efficient Transformer Adaptation with Soft Token Merging",
        BOOKTITLE = LargeVM24,
        YEAR = "2024",
        PAGES = "3658-3668",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150788"}

@inproceedings{bb154871,
        AUTHOR = "Xu, X. and Wang, S. and Chen, Y.D. and Zheng, Y.P. and Wei, Z.W. and Liu, J.J.",
        TITLE = "GTP-ViT: Efficient Vision Transformers via Graph-based Token
Propagation",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "86-95",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150789"}

@inproceedings{bb154872,
        AUTHOR = "Ding, S.R. and Zhao, P.S. and Zhang, X.P. and Qian, R. and Xiong, H.K. and Tian, Q.",
        TITLE = "Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "16899-16910",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150790"}

@inproceedings{bb154873,
        AUTHOR = "Guo, Y. and Stutz, D. and Schiele, B.",
        TITLE = "Improving Robustness of Vision Transformers by Reducing Sensitivity
to Patch Corruptions",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "4108-4118",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150791"}

@inproceedings{bb154874,
        AUTHOR = "Xie, W. and Zhao, Z. and Li, S.Y. and Zuo, B.H. and Wang, Y.G.",
        TITLE = "Nonrigid Object Contact Estimation With Regional Unwrapping
Transformer",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "9308-9317",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150792"}

@inproceedings{bb154875,
        AUTHOR = "Nalmpantis, A. and Panagiotopoulos, A. and Gkountouras, J. and Papakostas, K. and Aziz, W.",
        TITLE = "Vision DiffMask: Faithful Interpretation of Vision Transformers with
Differentiable Patch Masking",
        BOOKTITLE = XAI4CV23,
        YEAR = "2023",
        PAGES = "3756-3763",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150793"}

@inproceedings{bb154876,
        AUTHOR = "Beyer, L. and Izmailov, P. and Kolesnikov, A. and Caron, M. and Kornblith, S. and Zhai, X.H. and Minderer, M. and Tschannen, M. and Alabdulmohsin, I. and Pavetic, F.",
        TITLE = "FlexiViT: One Model for All Patch Sizes",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "14496-14506",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150794"}

@inproceedings{bb154877,
        AUTHOR = "Chang, S.N. and Wang, P. and Lin, M. and Wang, F. and Zhang, D.J.H. and Jin, R. and Shou, M.Z.",
        TITLE = "Making Vision Transformers Efficient from A Token Sparsification View",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "6195-6205",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150795"}

@inproceedings{bb154878,
        AUTHOR = "Phan, L. and Nguyen, H.T.H. and Warrier, H. and Gupta, Y.",
        TITLE = "Patch Embedding as Local Features: Unifying Deep Local and Global
Features via Vision Transformer for Image Retrieval",
        BOOKTITLE = ACCV22,
        YEAR = "2022",
        PAGES = "II:204-221",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150796"}

@inproceedings{bb154879,
        AUTHOR = "Liu, Y. and Matsoukas, C. and Strand, F. and Azizpour, H. and Smith, K.",
        TITLE = "PatchDropout: Economizing Vision Transformers Using Patch Dropout",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "3942-3951",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150797"}

@inproceedings{bb154880,
        AUTHOR = "Havtorn, J.D. and Royer, A. and Blankevoort, T. and Bejnordi, B.E.",
        TITLE = "MSViT: Dynamic Mixed-scale Tokenization for Vision Transformers",
        BOOKTITLE = NIVT23,
        YEAR = "2023",
        PAGES = "838-848",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150798"}

@inproceedings{bb154881,
        AUTHOR = "Haurum, J.B. and Escalera, S. and Taylor, G.W. and Moeslund, T.B.",
        TITLE = "Which Tokens to Use? Investigating Token Reduction in Vision
Transformers",
        BOOKTITLE = NIVT23,
        YEAR = "2023",
        PAGES = "773-783",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150799"}

@inproceedings{bb154882,
        AUTHOR = "Ren, S. and Yang, X.Y. and Liu, S. and Wang, X.C.",
        TITLE = "SG-Former: Self-guided Transformer with Evolving Token Reallocation",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "5980-5991",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150800"}

@inproceedings{bb154883,
        AUTHOR = "Xiao, H. and Zheng, W.Z. and Zhu, Z. and Zhou, J. and Lu, J.W.",
        TITLE = "Token-Label Alignment for Vision Transformers",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "5472-5481",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150801"}

@inproceedings{bb154884,
        AUTHOR = "Popovic, N. and Paudel, D.P. and Probst, T. and Van Gool, L.J.",
        TITLE = "Token-Consistent Dropout For Calibrated Vision Transformers",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "1030-1034",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150802"}

@inproceedings{bb154885,
        AUTHOR = "Wei, S.Y. and Ye, T.Z. and Zhang, S. and Tang, Y. and Liang, J.J.",
        TITLE = "Joint Token Pruning and Squeezing Towards More Aggressive Compression
of Vision Transformers",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "2092-2101",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150803"}

@inproceedings{bb154886,
        AUTHOR = "Zhang, J.P. and Huang, Y.Z. and Wu, W.B. and Lyu, M.R.",
        TITLE = "Transferable Adversarial Attacks on Vision Transformers with Token
Gradient Regularization",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "16415-16424",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150804"}

@inproceedings{bb154887,
        AUTHOR = "Ronen, T. and Levy, O. and Golbert, A.",
        TITLE = "Vision Transformers with Mixed-Resolution Tokenization",
        BOOKTITLE = ECV23,
        YEAR = "2023",
        PAGES = "4613-4622",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150805"}

@inproceedings{bb154888,
        AUTHOR = "Lorenzana, M.B. and Engstrom, C. and Chandra, S.S.",
        TITLE = "Transformer Compressed Sensing Via Global Image Tokens",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "3011-3015",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150806"}

@inproceedings{bb154889,
        AUTHOR = "Fayyaz, M. and Koohpayegani, S.A. and Jafari, F.R. and Sengupta, S. and Joze, H.R.V. and Sommerlade, E. and Pirsiavash, H. and Gall, J.",
        TITLE = "Adaptive Token Sampling for Efficient Vision Transformers",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XI:396-414",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150807"}

@inproceedings{bb154890,
        AUTHOR = "Kong, Z.L. and Dong, P.Y. and Ma, X.L. and Meng, X. and Niu, W. and Sun, M.S. and Shen, X. and Yuan, G. and Ren, B. and Tang, H. and Qin, M.H. and Wang, Y.Z.",
        TITLE = "SPViT:
Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XI:620-640",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150808"}

@inproceedings{bb154891,
        AUTHOR = "Fang, J. and Xie, L.X. and Wang, X.G. and Zhang, X.P. and Liu, W.Y. and Tian, Q.",
        TITLE = "MSG-Transformer:
Exchanging Local Spatial Information by Manipulating Messenger Tokens",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12053-12062",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150809"}

@inproceedings{bb154892,
        AUTHOR = "Yin, H.X. and Vahdat, A. and Alvarez, J.M. and Mallya, A. and Kautz, J. and Molchanov, P.",
        TITLE = "A-ViT: Adaptive Tokens for Efficient Vision Transformer",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "10799-10808",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150810"}

@inproceedings{bb154893,
        AUTHOR = "Gu, J.D. and Tresp, V. and Qin, Y.",
        TITLE = "Are Vision Transformers Robust to Patch Perturbations?",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XII:404-421",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150811"}

@inproceedings{bb154894,
        AUTHOR = "Li, Z.K. and Ma, L.P. and Chen, M.J. and Xiao, J.R. and Gu, Q.Y.",
        TITLE = "Patch Similarity Aware Data-Free Quantization for Vision Transformers",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XI:154-170",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150812"}

@inproceedings{bb154895,
        AUTHOR = "Yun, S. and Lee, H. and Kim, J. and Shin, J.",
        TITLE = "Patch-level Representation Learning for Self-supervised Vision
Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "8344-8353",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150813"}

@inproceedings{bb154896,
        AUTHOR = "Salman, H. and Jain, S. and Wong, E. and Madry, A.",
        TITLE = "Certified Patch Robustness via Smoothed Vision Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "15116-15126",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150814"}

@inproceedings{bb154897,
        AUTHOR = "Tang, Y.H. and Han, K. and Wang, Y.H. and Xu, C. and Guo, J.Y. and Xu, C. and Tao, D.C.",
        TITLE = "Patch Slimming for Efficient Vision Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12155-12164",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150815"}

@inproceedings{bb154898,
        AUTHOR = "Chen, Z.Y. and Li, B. and Wu, S. and Xu, J.H. and Ding, S.H. and Zhang, W.Q.",
        TITLE = "Shape Matters: Deformable Patch Attack",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "IV:529-548",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150816"}

@inproceedings{bb154899,
        AUTHOR = "Chen, Z.Y. and Li, B. and Xu, J.H. and Wu, S. and Ding, S.H. and Zhang, W.Q.",
        TITLE = "Towards Practical Certifiable Patch Defense with Vision Transformer",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "15127-15137",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651patvit5.html#TT150817"}