@inproceedings{bb160100,
AUTHOR = "Walmer, M. and Suri, S. and Gupta, K. and Shrivastava, A.",
TITLE = "Teaching Matters:
Investigating the Role of Supervision in Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "7486-7496",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155964"}
@inproceedings{bb160101,
AUTHOR = "Wang, S.G. and Xie, T. and Cheng, J. and Zhang, X.C. and Liu, H.J.",
TITLE = "MDL-NAS: A Joint Multi-domain Learning Framework for Vision
Transformer",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "20094-20104",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155965"}
@inproceedings{bb160102,
AUTHOR = "Ren, S. and Wei, F.Y. and Zhang, Z. and Hu, H.",
TITLE = "TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "3687-3697",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155966"}
@inproceedings{bb160103,
AUTHOR = "He, J.F. and Gao, Y. and Zhang, T.Z. and Zhang, Z. and Wu, F.",
TITLE = "D2Former: Jointly Learning Hierarchical Detectors and Contextual
Descriptors via Agent-Based Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2904-2914",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155967"}
@inproceedings{bb160104,
AUTHOR = "Chen, X.Y. and Liu, Z.J. and Tang, H.T. and Yi, L. and Zhao, H. and Han, S.",
TITLE = "SparseViT: Revisiting Activation Sparsity for Efficient
High-Resolution Vision Transformer",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2061-2070",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155968"}
@inproceedings{bb160105,
AUTHOR = "Lin, Y.B. and Bertasius, G.",
TITLE = "Siamese Vision Transformers are Scalable Audio-Visual Learners",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIV: 303-321",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155969"}
@inproceedings{bb160106,
AUTHOR = "Lin, Y.B. and Sung, Y.L. and Lei, J. and Bansal, M. and Bertasius, G.",
TITLE = "Vision Transformers are Parameter-Efficient Audio-Visual Learners",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2299-2309",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155970"}
@inproceedings{bb160107,
AUTHOR = "Das, R. and Dukler, Y. and Ravichandran, A. and Swaminathan, A.",
TITLE = "Learning Expressive Prompting With Residuals for Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "3366-3377",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155971"}
@inproceedings{bb160108,
AUTHOR = "Zheng, M.X. and Lou, Q. and Jiang, L.",
TITLE = "TrojViT: Trojan Insertion in Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "4025-4034",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155972"}
@inproceedings{bb160109,
AUTHOR = "Li, Y.X. and Xu, C.",
TITLE = "Trade-off between Robustness and Accuracy of Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "7558-7568",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155973"}
@inproceedings{bb160110,
AUTHOR = "Tarasiou, M. and Chavez, E. and Zafeiriou, S.",
TITLE = "ViTs for SITS: Vision Transformers for Satellite Image Time Series",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10418-10428",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155974"}
@inproceedings{bb160111,
AUTHOR = "Yu, Z.Z. and Wu, S. and Fu, Y.G. and Zhang, S. and Lin, Y.Y.C.",
TITLE = "Hint-Aug: Drawing Hints from Foundation Vision Transformers towards
Boosted Few-shot Parameter-Efficient Tuning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11102-11112",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155975"}
@inproceedings{bb160112,
AUTHOR = "Hou, J. and Dai, X.L. and He, Z.J. and Dai, A. and Nießner, M.",
TITLE = "Mask3D: Pretraining 2D Vision Transformers by Learning Masked 3D
Priors",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "13510-13519",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155976"}
@inproceedings{bb160113,
AUTHOR = "Xu, Z.Z. and Liu, R.K. and Yang, S. and Chai, Z.H. and Yuan, C.",
TITLE = "Learning Imbalanced Data with Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "15793-15803",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155977"}
@inproceedings{bb160114,
AUTHOR = "Yang, H. and Yin, H.X. and Shen, M. and Molchanov, P. and Li, H. and Kautz, J.",
TITLE = "Global Vision Transformer Pruning with Hessian-Aware Saliency",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18547-18557",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155978"}
@inproceedings{bb160115,
AUTHOR = "Nakamura, R. and Kataoka, H. and Takashima, S. and Noriega, E.J.M. and Yokota, R. and Inoue, N.",
TITLE = "Pre-training Vision Transformers with Very Limited Synthesized Images",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20303-20312",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155979"}
@inproceedings{bb160116,
AUTHOR = "Takashima, S. and Hayamizu, R. and Inoue, N. and Kataoka, H. and Yokota, R.",
TITLE = "Visual Atoms: Pre-Training Vision Transformers with Sinusoidal Waves",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18579-18588",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155980"}
@inproceedings{bb160117,
AUTHOR = "Liu, Y.J. and Yang, H.R. and Dong, Z. and Keutzer, K. and Du, L. and Zhang, S.H.",
TITLE = "NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization
for Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "20321-20330",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155981"}
@inproceedings{bb160118,
AUTHOR = "Park, J. and Johnson, J.",
TITLE = "RGB No More: Minimally-Decoded JPEG Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22334-22346",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155982"}
@inproceedings{bb160119,
AUTHOR = "Yu, C. and Chen, T. and Gan, Z.X. and Fan, J.Y.",
TITLE = "Boost Vision Transformer with GPU-Friendly Sparsity and Quantization",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22658-22668",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155983"}
@inproceedings{bb160120,
AUTHOR = "Bao, F. and Nie, S. and Xue, K.W. and Cao, Y. and Li, C.X. and Su, H. and Zhu, J.",
TITLE = "All are Worth Words: A ViT Backbone for Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22669-22679",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155984"}
@inproceedings{bb160121,
AUTHOR = "Li, B. and Hu, Y.H. and Nie, X.C. and Han, C.Y. and Jiang, X.J. and Guo, T.D. and Liu, L.Q.",
TITLE = "DropKey for Vision Transformer",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22700-22709",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT155985"}
@inproceedings{bb160122,
AUTHOR = "Lan, S.Y. and Yang, X.T. and Yu, Z.D. and Wu, Z.X. 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#TT155986"}
@inproceedings{bb160123,
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#TT155987"}
@inproceedings{bb160124,
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#TT155988"}
@inproceedings{bb160125,
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#TT155989"}
@inproceedings{bb160126,
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#TT155990"}
@inproceedings{bb160127,
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#TT155991"}
@inproceedings{bb160128,
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#TT155992"}
@inproceedings{bb160129,
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#TT155993"}
@inproceedings{bb160130,
AUTHOR = "Ma, D.N. 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#TT155994"}
@inproceedings{bb160131,
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#TT155995"}
@inproceedings{bb160132,
AUTHOR = "Tian, R. and Wu, Z.X. 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#TT155996"}
@inproceedings{bb160133,
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#TT155997"}
@inproceedings{bb160134,
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#TT155998"}
@inproceedings{bb160135,
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#TT155999"}
@inproceedings{bb160136,
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#TT156000"}
@inproceedings{bb160137,
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#TT156001"}
@inproceedings{bb160138,
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#TT156002"}
@inproceedings{bb160139,
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#TT156003"}
@inproceedings{bb160140,
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#TT156004"}
@inproceedings{bb160141,
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#TT156005"}
@inproceedings{bb160142,
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#TT156006"}
@inproceedings{bb160143,
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#TT156007"}
@inproceedings{bb160144,
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#TT156008"}
@inproceedings{bb160145,
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#TT156009"}
@inproceedings{bb160146,
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#TT156010"}
@inproceedings{bb160147,
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#TT156011"}
@inproceedings{bb160148,
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#TT156012"}
@inproceedings{bb160149,
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#TT156013"}
@inproceedings{bb160150,
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#TT156014"}
@inproceedings{bb160151,
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#TT156015"}
@inproceedings{bb160152,
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#TT156016"}
@inproceedings{bb160153,
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#TT156017"}
@inproceedings{bb160154,
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#TT156018"}
@inproceedings{bb160155,
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#TT156019"}
@inproceedings{bb160156,
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#TT156020"}
@inproceedings{bb160157,
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#TT156021"}
@inproceedings{bb160158,
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#TT156022"}
@inproceedings{bb160159,
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#TT156023"}
@inproceedings{bb160160,
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#TT156024"}
@inproceedings{bb160161,
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#TT156025"}
@inproceedings{bb160162,
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#TT156026"}
@inproceedings{bb160163,
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#TT156027"}
@inproceedings{bb160164,
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#TT156028"}
@inproceedings{bb160165,
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#TT156029"}
@inproceedings{bb160166,
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#TT156030"}
@inproceedings{bb160167,
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#TT156031"}
@inproceedings{bb160168,
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#TT156032"}
@inproceedings{bb160169,
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#TT156033"}
@inproceedings{bb160170,
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#TT156034"}
@inproceedings{bb160171,
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#TT156035"}
@inproceedings{bb160172,
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#TT156036"}
@inproceedings{bb160173,
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#TT156037"}
@inproceedings{bb160174,
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#TT156038"}
@inproceedings{bb160175,
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#TT156039"}
@inproceedings{bb160176,
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#TT156040"}
@inproceedings{bb160177,
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#TT156041"}
@inproceedings{bb160178,
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#TT156042"}
@inproceedings{bb160179,
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#TT156043"}
@inproceedings{bb160180,
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#TT156044"}
@inproceedings{bb160181,
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#TT156045"}
@inproceedings{bb160182,
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#TT156046"}
@inproceedings{bb160183,
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#TT156047"}
@inproceedings{bb160184,
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#TT156048"}
@inproceedings{bb160185,
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#TT156049"}
@inproceedings{bb160186,
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#TT156050"}
@inproceedings{bb160187,
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#TT156051"}
@inproceedings{bb160188,
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#TT156052"}
@inproceedings{bb160189,
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#TT156053"}
@inproceedings{bb160190,
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#TT156054"}
@inproceedings{bb160191,
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#TT156055"}
@inproceedings{bb160192,
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#TT156056"}
@inproceedings{bb160193,
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#TT156057"}
@inproceedings{bb160194,
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#TT156058"}
@inproceedings{bb160195,
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#TT156059"}
@inproceedings{bb160196,
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#TT156060"}
@inproceedings{bb160197,
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#TT156061"}
@inproceedings{bb160198,
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#TT156062"}
@inproceedings{bb160199,
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#TT156063"}
Last update:Aug 19, 2026 at 13:26:35