@inproceedings{bb145900,
AUTHOR = "Lan, S.Y. and Yang, X.T. and Yu, Z.D. and Wu, Z. and Alvarez, J.M. and Anandkumar, A.",
TITLE = "Vision Transformers are Good Mask Auto-Labelers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "23745-23755",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141832"}
@inproceedings{bb145901,
AUTHOR = "Yu, L. and Xiang, W.",
TITLE = "X-Pruner: eXplainable Pruning for Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "24355-24363",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141833"}
@inproceedings{bb145902,
AUTHOR = "Singh, A.",
TITLE = "Training Strategies for Vision Transformers for Object Detection",
BOOKTITLE = WAD23,
YEAR = "2023",
PAGES = "110-118",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141834"}
@inproceedings{bb145903,
AUTHOR = "Hukkelas, H. and Lindseth, F.",
TITLE = "Does Image Anonymization Impact Computer Vision Training?",
BOOKTITLE = WAD23,
YEAR = "2023",
PAGES = "140-150",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141835"}
@inproceedings{bb145904,
AUTHOR = "Marnissi, M.A.",
TITLE = "Revolutionizing Thermal Imaging: GAN-Based Vision Transformers for
Image Enhancement",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "2735-2739",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141836"}
@inproceedings{bb145905,
AUTHOR = "Marnissi, M.A. and Fathallah, A.",
TITLE = "GAN-based Vision Transformer for High-Quality Thermal Image
Enhancement",
BOOKTITLE = GCV23,
YEAR = "2023",
PAGES = "817-825",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141837"}
@inproceedings{bb145906,
AUTHOR = "Scheibenreif, L. and Mommert, M. and Borth, D.",
TITLE = "Masked Vision Transformers for Hyperspectral Image Classification",
BOOKTITLE = EarthVision23,
YEAR = "2023",
PAGES = "2166-2176",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141838"}
@inproceedings{bb145907,
AUTHOR = "Komorowski, P. and Baniecki, H. and Biecek, P.",
TITLE = "Towards Evaluating Explanations of Vision Transformers for Medical
Imaging",
BOOKTITLE = XAI4CV23,
YEAR = "2023",
PAGES = "3726-3732",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141839"}
@inproceedings{bb145908,
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/pattern651vit2.html#TT141840"}
@inproceedings{bb145909,
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/pattern651vit2.html#TT141841"}
@inproceedings{bb145910,
AUTHOR = "Le, P.H.C. and Li, X.",
TITLE = "BinaryViT: Pushing Binary Vision Transformers Towards Convolutional
Models",
BOOKTITLE = ECV23,
YEAR = "2023",
PAGES = "4665-4674",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141842"}
@inproceedings{bb145911,
AUTHOR = "Ma, D. and Zhao, P.F. and Jiao, X.",
TITLE = "PerfHD: Efficient ViT Architecture Performance Ranking using
Hyperdimensional Computing",
BOOKTITLE = NAS23,
YEAR = "2023",
PAGES = "2230-2237",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141843"}
@inproceedings{bb145912,
AUTHOR = "Wang, J. and Alamayreh, O. and Tondi, B. and Barni, M.",
TITLE = "Open Set Classification of GAN-based Image Manipulations via a
ViT-based Hybrid Architecture",
BOOKTITLE = WMF23,
YEAR = "2023",
PAGES = "953-962",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141844"}
@inproceedings{bb145913,
AUTHOR = "Tian, R. and Wu, Z. and Dai, Q. and Hu, H. and Qiao, Y. and Jiang, Y.G.",
TITLE = "ResFormer: Scaling ViTs with Multi-Resolution Training",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22721-22731",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141845"}
@inproceedings{bb145914,
AUTHOR = "Li, Y. and Min, K. and Tripathi, S. and Vasconcelos, N.M.",
TITLE = "SViTT: Temporal Learning of Sparse Video-Text Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18919-18929",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141846"}
@inproceedings{bb145915,
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/pattern651vit2.html#TT141847"}
@inproceedings{bb145916,
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/pattern651vit2.html#TT141848"}
@inproceedings{bb145917,
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/pattern651vit2.html#TT141849"}
@inproceedings{bb145918,
AUTHOR = "Guo, X.D. and Sun, Y. and Zhao, R. and Kuang, L.Q. and Han, X.",
TITLE = "SWPT: Spherical Window-based Point Cloud Transformer",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "I:396-412",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141850"}
@inproceedings{bb145919,
AUTHOR = "Wang, W.J. and Chen, G. and Zhou, H.R. and Wang, X.L.",
TITLE = "OVPT: Optimal Viewset Pooling Transformer for 3d Object Recognition",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "I:486-503",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141851"}
@inproceedings{bb145920,
AUTHOR = "Kim, D. and Kim, J.",
TITLE = "Vision Transformer Compression and Architecture Exploration with
Efficient Embedding Space Search",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "III:524-540",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141852"}
@inproceedings{bb145921,
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#TT141853"}
@inproceedings{bb145922,
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#TT141854"}
@inproceedings{bb145923,
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#TT141855"}
@inproceedings{bb145924,
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#TT141856"}
@inproceedings{bb145925,
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#TT141857"}
@inproceedings{bb145926,
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/pattern651vit2.html#TT141858"}
@inproceedings{bb145927,
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#TT141859"}
@inproceedings{bb145928,
AUTHOR = "Yang, J. 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#TT141860"}
@inproceedings{bb145929,
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#TT141861"}
@inproceedings{bb145930,
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#TT141862"}
@inproceedings{bb145931,
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#TT141863"}
@inproceedings{bb145932,
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#TT141864"}
@inproceedings{bb145933,
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#TT141865"}
@inproceedings{bb145934,
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/pattern651vit2.html#TT141866"}
@inproceedings{bb145935,
AUTHOR = "Lu, X.Y. and Du, S.",
TITLE = "NCTR: Neighborhood Consensus Transformer for Feature Matching",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2726-2730",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141867"}
@inproceedings{bb145936,
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#TT141868"}
@inproceedings{bb145937,
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#TT141869"}
@inproceedings{bb145938,
AUTHOR = "Li, K. and Yu, R. and Wang, Z. 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#TT141870"}
@inproceedings{bb145939,
AUTHOR = "Tu, Z.Z. and Talebi, H. and Zhang, H. and Yang, F. and Milanfar, P. and Bovik, A.C. and Li, Y.",
TITLE = "MaxViT: Multi-axis Vision Transformer",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIV:459-479",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141871"}
@inproceedings{bb145940,
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#TT141872"}
@inproceedings{bb145941,
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#TT141873"}
@inproceedings{bb145942,
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#TT141874"}
@inproceedings{bb145943,
AUTHOR = "Li, Y.H. and Mao, H.Z. and Girshick, R. and He, K.M.",
TITLE = "Exploring Plain Vision Transformer Backbones for Object Detection",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "IX:280-296",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141875"}
@inproceedings{bb145944,
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#TT141876"}
@inproceedings{bb145945,
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#TT141877"}
@inproceedings{bb145946,
AUTHOR = "Yu, W.X. and Zhang, H. and Lan, T.X. and Hu, Y.C. and Yin, D.",
TITLE = "CBPT: A New Backbone for Enhancing Information Transmission of Vision
Transformers",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "156-160",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141878"}
@inproceedings{bb145947,
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#TT141879"}
@inproceedings{bb145948,
AUTHOR = "Zhou, W.L. and Kamata, S.I. and Luo, Z. 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#TT141880"}
@inproceedings{bb145949,
AUTHOR = "Li, J. and Zhang, H. and Xie, C.",
TITLE = "ViP: Unified Certified Detection and Recovery for Patch Attack with
Vision Transformers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXV:573-587",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141881"}
@inproceedings{bb145950,
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#TT141882"}
@inproceedings{bb145951,
AUTHOR = "Wang, C. and Xu, H.M. and Zhang, X. and Wang, L. and Zheng, Z. 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#TT141883"}
@inproceedings{bb145952,
AUTHOR = "Wu, B. 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#TT141884"}
@inproceedings{bb145953,
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/pattern651vit2.html#TT141885"}
@inproceedings{bb145954,
AUTHOR = "Zong, Z. and Li, K. and Song, G. 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#TT141886"}
@inproceedings{bb145955,
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/pattern651vit2.html#TT141887"}
@inproceedings{bb145956,
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/pattern651vit2.html#TT141888"}
@inproceedings{bb145957,
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#TT141889"}
@inproceedings{bb145958,
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#TT141890"}
@inproceedings{bb145959,
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#TT141891"}
@inproceedings{bb145960,
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#TT141892"}
@inproceedings{bb145961,
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#TT141893"}
@inproceedings{bb145962,
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#TT141894"}
@inproceedings{bb145963,
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#TT141895"}
@inproceedings{bb145964,
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/pattern651vit2.html#TT141896"}
@inproceedings{bb145965,
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#TT141897"}
@inproceedings{bb145966,
AUTHOR = "Xiang, H. and Xu, R.S. and Ma, J.Q.",
TITLE = "HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative Perception with
Vision Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "284-295",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141898"}
@inproceedings{bb145967,
AUTHOR = "Xu, R.S. and Xiang, H. and Tu, Z.Z. and Xia, X. and Yang, M.H. and Ma, J.Q.",
TITLE = "V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision
Transformer",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:107-124",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141899"}
@inproceedings{bb145968,
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#TT141900"}
@inproceedings{bb145969,
AUTHOR = "Ren, P.Z. and Li, C. and Wang, G. 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#TT141901"}
@inproceedings{bb145970,
AUTHOR = "Bhattacharjee, D. and Zhang, T. and Susstrunk, S. and Salzmann, M.",
TITLE = "MuIT: An End-to-End Multitask Learning Transformer",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "12021-12031",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141902"}
@inproceedings{bb145971,
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/pattern651vit2.html#TT141903"}
@inproceedings{bb145972,
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#TT141904"}
@inproceedings{bb145973,
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#TT141905"}
@inproceedings{bb145974,
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#TT141906"}
@inproceedings{bb145975,
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#TT141907"}
@inproceedings{bb145976,
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/pattern651vit2.html#TT141908"}
@inproceedings{bb145977,
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#TT141909"}
@inproceedings{bb145978,
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/pattern651vit2.html#TT141910"}
@inproceedings{bb145979,
AUTHOR = "Wang, Y.K. and Chen, X.H. and Cao, L. and Huang, W.B. and Sun, F.C. and Wang, Y.H.",
TITLE = "Multimodal Token Fusion for Vision Transformers",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "12176-12185",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141911"}
@inproceedings{bb145980,
AUTHOR = "Tang, Y. 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/pattern651vit2.html#TT141912"}
@inproceedings{bb145981,
AUTHOR = "Zhang, J. and Peng, H. 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#TT141913"}
@inproceedings{bb145982,
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#TT141914"}
@inproceedings{bb145983,
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/pattern651vit2.html#TT141915"}
@inproceedings{bb145984,
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#TT141916"}
@inproceedings{bb145985,
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#TT141917"}
@inproceedings{bb145986,
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#TT141918"}
@inproceedings{bb145987,
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#TT141919"}
@inproceedings{bb145988,
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/pattern651vit2.html#TT141920"}
@inproceedings{bb145989,
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/pattern651vit2.html#TT141921"}
@inproceedings{bb145990,
AUTHOR = "Chen, R.J. and Chen, C. 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#TT141922"}
@inproceedings{bb145991,
AUTHOR = "Yang, Z. and Wang, J.Q. and Tang, Y.S. and Chen, K. and Zhao, H.S. and Torr, P.H.S.",
TITLE = "LAVT: Language-Aware Vision Transformer for Referring Image
Segmentation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18134-18144",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141923"}
@inproceedings{bb145992,
AUTHOR = "Scheibenreif, L. and Hanna, J. and Mommert, M. and Borth, D.",
TITLE = "Self-supervised Vision Transformers for Land-cover Segmentation and
Classification",
BOOKTITLE = EarthVision22,
YEAR = "2022",
PAGES = "1421-1430",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141924"}
@inproceedings{bb145993,
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#TT141925"}
@inproceedings{bb145994,
AUTHOR = "Guo, J.Y. and Han, K. and Wu, H. and Tang, Y. and Chen, X.H. and Wang, Y.H. and Xu, C.",
TITLE = "CMT: Convolutional Neural Networks Meet Vision Transformers",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "12165-12175",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT141926"}
@inproceedings{bb145995,
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#TT141927"}
@inproceedings{bb145996,
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#TT141928"}
@inproceedings{bb145997,
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#TT141929"}
@inproceedings{bb145998,
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#TT141930"}
@inproceedings{bb145999,
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#TT141931"}
Last update:Nov 26, 2024 at 16:40:19