@inproceedings{bb157200,
AUTHOR = "Lee, Y.S. and Lee, G. and Ryoo, K. and Go, H. and Park, J. and Kim, S.",
TITLE = "Towards Flexible Inductive Bias via Progressive Reparameterization
Scheduling",
BOOKTITLE = VIPriors22,
YEAR = "2022",
PAGES = "706-720",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153072"}
@inproceedings{bb157201,
AUTHOR = "Amir, S. and Gandelsman, Y. and Bagon, S. and Dekel, T.",
TITLE = "On the Effectiveness of VIT Features as Local Semantic Descriptors",
BOOKTITLE = SelfLearn22,
YEAR = "2022",
PAGES = "39-55",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153073"}
@inproceedings{bb157202,
AUTHOR = "Deng, X. and Liu, C.B. and Lu, Z.Y.",
TITLE = "Recombining Vision Transformer Architecture for Fine-grained Visual
Categorization",
BOOKTITLE = MMMod23,
YEAR = "2023",
PAGES = "II: 127-138",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153074"}
@inproceedings{bb157203,
AUTHOR = "Tonkes, V. and Sabatelli, M.",
TITLE = "How Well Do Vision Transformers (vts) Transfer to the Non-natural Image
Domain? An Empirical Study Involving Art Classification",
BOOKTITLE = VisArt22,
YEAR = "2022",
PAGES = "234-250",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153075"}
@inproceedings{bb157204,
AUTHOR = "Rangrej, S.B. and Liang, K.J. and Hassner, T. and Clark, J.J.",
TITLE = "GliTr: Glimpse Transformers with Spatiotemporal Consistency for
Online Action Prediction",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "3402-3412",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153076"}
@inproceedings{bb157205,
AUTHOR = "Song, C.H. and Yoon, J.Y. and Choi, S. and Avrithis, Y.",
TITLE = "Boosting vision transformers for image retrieval",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "107-117",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153077"}
@inproceedings{bb157206,
AUTHOR = "Yang, J.Y. and Liu, J.J. and Xu, N. and Huang, J.Z.",
TITLE = "TVT: Transferable Vision Transformer for Unsupervised Domain
Adaptation",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "520-530",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153078"}
@inproceedings{bb157207,
AUTHOR = "Saavedra Ruiz, M. and Morin, S. and Paull, L.",
TITLE = "Monocular Robot Navigation with Self-Supervised Pretrained Vision
Transformers",
BOOKTITLE = CRV22,
YEAR = "2022",
PAGES = "197-204",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153079"}
@inproceedings{bb157208,
AUTHOR = "Patel, K. and Bur, A.M. and Li, F.J. and Wang, G.H.",
TITLE = "Aggregating Global Features into Local Vision Transformer",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "1141-1147",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153080"}
@inproceedings{bb157209,
AUTHOR = "Shen, Z.Q. and Liu, Z. and Xing, E.",
TITLE = "Sliced Recursive Transformer",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIV:727-744",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153081"}
@inproceedings{bb157210,
AUTHOR = "Shao, Y. and Loy, C.C. and Dai, B.",
TITLE = "Transformer with Implicit Edges for Particle-Based Physics Simulation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XIX:549-564",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153082"}
@inproceedings{bb157211,
AUTHOR = "Wang, W. and Zhang, J. and Cao, Y. and Shen, Y.L. and Tao, D.C.",
TITLE = "Towards Data-Efficient Detection Transformers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "IX:88-105",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153083"}
@inproceedings{bb157212,
AUTHOR = "Lu, X.Y. and Du, S.L.",
TITLE = "NCTR: Neighborhood Consensus Transformer for Feature Matching",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2726-2730",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153084"}
@inproceedings{bb157213,
AUTHOR = "Noohi, E.A. and Imani, H. and Islam, M.B.",
TITLE = "MLP Fusion: Revisiting Convolutional Networks with Transformer-Based
Insights",
BOOKTITLE = IPTA25,
YEAR = "2025",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153085"}
@inproceedings{bb157214,
AUTHOR = "Jeny, A.A. and Junayed, M.S. and Islam, M.B.",
TITLE = "An Efficient End-To-End Image Compression Transformer",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "1786-1790",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153086"}
@inproceedings{bb157215,
AUTHOR = "Bai, J.W. and Yuan, L. and Xia, S.T. and Yan, S.C. and Li, Z.F. and Liu, W.",
TITLE = "Improving Vision Transformers by Revisiting High-Frequency Components",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIV:1-18",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153087"}
@inproceedings{bb157216,
AUTHOR = "Li, K. and Yu, R. and Wang, Z.N. and Yuan, L. and Song, G. and Chen, J.",
TITLE = "Locality Guidance for Improving Vision Transformers on Tiny Datasets",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIV:110-127",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153088"}
@inproceedings{bb157217,
AUTHOR = "Tu, Z.Z. and Talebi, H. and Zhang, H. and Yang, F. and Milanfar, P. and Bovik, A.C. and Li, Y.X.",
TITLE = "MaxViT: Multi-axis Vision Transformer",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIV:459-479",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153089"}
@inproceedings{bb157218,
AUTHOR = "Yang, R. and Ma, H.L. and Wu, J. and Tang, Y.S. and Xiao, X.F. and Zheng, M. and Li, X.",
TITLE = "ScalableViT: Rethinking the Context-Oriented Generalization of Vision
Transformer",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIV:480-496",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153090"}
@inproceedings{bb157219,
AUTHOR = "Touvron, H. and Cord, M. and El Nouby, A. and Verbeek, J. and Jegou, H.",
TITLE = "Three Things Everyone Should Know About Vision Transformers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIV:497-515",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153091"}
@inproceedings{bb157220,
AUTHOR = "Touvron, H. and Cord, M. and Jegou, H.",
TITLE = "DeiT III: Revenge of the ViT",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIV:516-533",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153092"}
@inproceedings{bb157221,
AUTHOR = "Yu, Q.H. and Wang, H.Y. and Qiao, S.Y. and Collins, M. and Zhu, Y.K. and Adam, H. and Yuille, A.L. and Chen, L.C.",
TITLE = "k-means Mask Transformer",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:288-307",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153093"}
@inproceedings{bb157222,
AUTHOR = "Pham, K. and Kafle, K. and Lin, Z. and Ding, Z.H. and Cohen, S. and Tran, Q. and Shrivastava, A.",
TITLE = "Improving Closed and Open-Vocabulary Attribute Prediction Using
Transformers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXV:201-219",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153094"}
@inproceedings{bb157223,
AUTHOR = "Takeda, M. and Yanai, K.",
TITLE = "Continual Learning in Vision Transformer",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "616-620",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153095"}
@inproceedings{bb157224,
AUTHOR = "Zhou, W.L. and Kamata, S.I. and Luo, Z.B. and Xue, X.",
TITLE = "Rethinking Unified Spectral-Spatial-Based Hyperspectral Image
Classification Under 3D Configuration of Vision Transformer",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "711-715",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153096"}
@inproceedings{bb157225,
AUTHOR = "Cao, Y.H. and Yu, H. and Wu, J.X.",
TITLE = "Training Vision Transformers with only 2040 Images",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXV:220-237",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153097"}
@inproceedings{bb157226,
AUTHOR = "Wang, C. and Xu, H.M. and Zhang, X. and Wang, L. and Zheng, Z.T. and Liu, H.F.",
TITLE = "Convolutional Embedding Makes Hierarchical Vision Transformer Stronger",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XX:739-756",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153098"}
@inproceedings{bb157227,
AUTHOR = "Wu, B.X. and Gu, J.D. and Li, Z.F. and Cai, D. and He, X.F. and Liu, W.",
TITLE = "Towards Efficient Adversarial Training on Vision Transformers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XIII:307-325",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153099"}
@inproceedings{bb157228,
AUTHOR = "Zong, Z.F. and Li, K.C. and Song, G.L. and Wang, Y. and Qiao, Y. and Leng, B. and Liu, Y.",
TITLE = "Self-slimmed Vision Transformer",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XI:432-448",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153100"}
@inproceedings{bb157229,
AUTHOR = "Weng, Z.J. and Yang, X.T. and Li, A. and Wu, Z.X. and Jiang, Y.G.",
TITLE = "Semi-supervised Vision Transformers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXX:605-620",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153101"}
@inproceedings{bb157230,
AUTHOR = "Su, T. and Ye, S. and Song, C.Q. and Cheng, J.",
TITLE = "Mask-Vit: an Object Mask Embedding in Vision Transformer for
Fine-Grained Visual Classification",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "1626-1630",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153102"}
@inproceedings{bb157231,
AUTHOR = "Gai, L. and Chen, W. and Gao, R. and Chen, Y.W. and Qiao, X.",
TITLE = "Using Vision Transformers in 3-D Medical Image Classifications",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "696-700",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153103"}
@inproceedings{bb157232,
AUTHOR = "Wu, K. and Zhang, J. and Peng, H. and Liu, M.C. and Xiao, B. and Fu, J.L. and Yuan, L.",
TITLE = "TinyViT: Fast Pretraining Distillation for Small Vision Transformers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXI:68-85",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153104"}
@inproceedings{bb157233,
AUTHOR = "Gao, L. and Nie, D. and Li, B. and Ren, X.F.",
TITLE = "Doubly-Fused ViT: Fuse Information from Vision Transformer Doubly with
Local Representation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIII:744-761",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153105"}
@inproceedings{bb157234,
AUTHOR = "Yao, T. and Pan, Y.W. and Li, Y. and Ngo, C.W. and Mei, T.",
TITLE = "Wave-ViT: Unifying Wavelet and Transformers for Visual Representation
Learning",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXV:328-345",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153106"}
@inproceedings{bb157235,
AUTHOR = "Yuan, Z.H. and Xue, C.H. and Chen, Y.Q. and Wu, Q. and Sun, G.Y.",
TITLE = "PTQ4ViT: Post-training Quantization for Vision Transformers with Twin
Uniform Quantization",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XII:191-207",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153107"}
@inproceedings{bb157236,
AUTHOR = "Pan, J.T. and Bulat, A. and Tan, F. and Zhu, X.T. and Dudziak, L. and Li, H.S. and Tzimiropoulos, G. and Martinez, B.",
TITLE = "EdgeViTs: Competing Light-Weight CNNs on Mobile Devices with Vision
Transformers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XI:294-311",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153108"}
@inproceedings{bb157237,
AUTHOR = "Liu, Y. and Mai, S.Q. and Chen, X.N. and Hsieh, C.J. and You, Y.",
TITLE = "Towards Efficient and Scalable Sharpness-Aware Minimization",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "12350-12360",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153109"}
@inproceedings{bb157238,
AUTHOR = "Ren, P.Z. and Li, C.L. and Wang, G.R. and Xiao, Y. and Du, Q. and Liang, X.D. and Chang, X.J.",
TITLE = "Beyond Fixation: Dynamic Window Visual Transformer",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "11977-11987",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153110"}
@inproceedings{bb157239,
AUTHOR = "Sandler, M. and Zhmoginov, A. and Vladymyrov, M. and Jackson, A.",
TITLE = "Fine-tuning Image Transformers using Learnable Memory",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "12145-12154",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153111"}
@inproceedings{bb157240,
AUTHOR = "Yu, X. and Tang, L. and Rao, Y.M. and Huang, T.J. and Zhou, J. and Lu, J.W.",
TITLE = "Point-BERT: Pre-training 3D Point Cloud Transformers with Masked
Point Modeling",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19291-19300",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153112"}
@inproceedings{bb157241,
AUTHOR = "Park, C. and Jeong, Y. and Cho, M. and Park, J.",
TITLE = "Fast Point Transformer",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16928-16937",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT153113"}
@inproceedings{bb157242,
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#TT153114"}
@inproceedings{bb157243,
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#TT153115"}
@inproceedings{bb157244,
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#TT153116"}
@inproceedings{bb157245,
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#TT153117"}
@inproceedings{bb157246,
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#TT153118"}
@inproceedings{bb157247,
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#TT153119"}
@inproceedings{bb157248,
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#TT153120"}
@inproceedings{bb157249,
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#TT153121"}
@inproceedings{bb157250,
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#TT153122"}
@inproceedings{bb157251,
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#TT153123"}
@inproceedings{bb157252,
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#TT153124"}
@inproceedings{bb157253,
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#TT153125"}
@inproceedings{bb157254,
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#TT153126"}
@inproceedings{bb157255,
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#TT153127"}
@inproceedings{bb157256,
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#TT153128"}
@inproceedings{bb157257,
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#TT153129"}
@inproceedings{bb157258,
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#TT153130"}
@inproceedings{bb157259,
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#TT153131"}
@inproceedings{bb157260,
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#TT153132"}
@inproceedings{bb157261,
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#TT153133"}
@inproceedings{bb157262,
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#TT153134"}
@inproceedings{bb157263,
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#TT153135"}
@inproceedings{bb157264,
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#TT153136"}
@inproceedings{bb157265,
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#TT153137"}
@inproceedings{bb157266,
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#TT153138"}
@inproceedings{bb157267,
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#TT153139"}
@inproceedings{bb157268,
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#TT153140"}
@inproceedings{bb157269,
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#TT153141"}
@inproceedings{bb157270,
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#TT153142"}
@inproceedings{bb157271,
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#TT153143"}
@inproceedings{bb157272,
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#TT153144"}
@inproceedings{bb157273,
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#TT153145"}
@inproceedings{bb157274,
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#TT153146"}
@inproceedings{bb157275,
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#TT153147"}
@inproceedings{bb157276,
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#TT153148"}
@inproceedings{bb157277,
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#TT153149"}
@inproceedings{bb157278,
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#TT153150"}
@inproceedings{bb157279,
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#TT153151"}
@inproceedings{bb157280,
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#TT153152"}
@inproceedings{bb157281,
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#TT153153"}
@inproceedings{bb157282,
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#TT153154"}
@inproceedings{bb157283,
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#TT153155"}
@inproceedings{bb157284,
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#TT153156"}
@inproceedings{bb157285,
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#TT153157"}
@inproceedings{bb157286,
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#TT153158"}
@inproceedings{bb157287,
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#TT153159"}
@inproceedings{bb157288,
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#TT153160"}
@article{bb157289,
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#TT153161"}
@article{bb157290,
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#TT153162"}
@article{bb157291,
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#TT153163"}
@article{bb157292,
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#TT153164"}
@article{bb157293,
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#TT153165"}
@article{bb157294,
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#TT153166"}
@article{bb157295,
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#TT153167"}
@article{bb157296,
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#TT153168"}
@article{bb157297,
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#TT153169"}
@article{bb157298,
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#TT153170"}
@article{bb157299,
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#TT153171"}
Last update:Feb 26, 2026 at 10:58:24