@inproceedings{bb158200,
AUTHOR = "Sajjadi, M.S.M. and Mahendran, A. and Kipf, T. and Pot, E. and Duckworth, D. and Lucic, M. and Greff, K.",
TITLE = "RUST: Latent Neural Scene Representations from Unposed Imagery",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "17297-17306",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT154070"}
@inproceedings{bb158201,
AUTHOR = "Bowman, B. and Achille, A. and Zancato, L. and Trager, M. and Perera, P. and Paolini, G. and Soatto, S.",
TITLE = "À-la-carte Prompt Tuning (APT):
Combining Distinct Data Via Composable Prompting",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14984-14993",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT154071"}
@inproceedings{bb158202,
AUTHOR = "Nakhli, R. and Moghadam, P.A. and Mi, H.Y. and Farahani, H. and Baras, A. and Gilks, B. and Bashashati, A.",
TITLE = "Sparse Multi-Modal Graph Transformer with Shared-Context Processing
for Representation Learning of Giga-pixel Images",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11547-11557",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT154072"}
@inproceedings{bb158203,
AUTHOR = "Gartner, E. and Metz, L. and Andriluka, M. and Freeman, C.D. and Sminchisescu, C.",
TITLE = "Transformer-Based Learned Optimization",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11970-11979",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT154073"}
@inproceedings{bb158204,
AUTHOR = "Li, J.C. and Hassani, A. and Walton, S. and Shi, H.",
TITLE = "ConvMLP: Hierarchical Convolutional MLPs for Vision",
BOOKTITLE = WFM23,
YEAR = "2023",
PAGES = "6307-6316",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT154074"}
@inproceedings{bb158205,
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#TT154075"}
@inproceedings{bb158206,
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#TT154076"}
@inproceedings{bb158207,
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#TT154077"}
@inproceedings{bb158208,
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#TT154078"}
@inproceedings{bb158209,
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#TT154079"}
@inproceedings{bb158210,
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#TT154080"}
@inproceedings{bb158211,
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#TT154081"}
@inproceedings{bb158212,
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#TT154082"}
@inproceedings{bb158213,
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#TT154083"}
@inproceedings{bb158214,
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#TT154084"}
@inproceedings{bb158215,
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#TT154085"}
@inproceedings{bb158216,
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#TT154086"}
@inproceedings{bb158217,
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#TT154087"}
@inproceedings{bb158218,
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#TT154088"}
@inproceedings{bb158219,
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#TT154089"}
@inproceedings{bb158220,
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#TT154090"}
@inproceedings{bb158221,
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#TT154091"}
@inproceedings{bb158222,
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#TT154092"}
@inproceedings{bb158223,
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#TT154093"}
@inproceedings{bb158224,
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#TT154094"}
@inproceedings{bb158225,
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#TT154095"}
@inproceedings{bb158226,
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#TT154096"}
@inproceedings{bb158227,
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#TT154097"}
@inproceedings{bb158228,
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#TT154098"}
@inproceedings{bb158229,
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#TT154099"}
@inproceedings{bb158230,
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#TT154100"}
@inproceedings{bb158231,
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#TT154101"}
@inproceedings{bb158232,
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#TT154102"}
@inproceedings{bb158233,
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#TT154103"}
@inproceedings{bb158234,
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#TT154104"}
@inproceedings{bb158235,
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#TT154105"}
@inproceedings{bb158236,
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#TT154106"}
@inproceedings{bb158237,
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#TT154107"}
@inproceedings{bb158238,
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#TT154108"}
@inproceedings{bb158239,
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#TT154109"}
@inproceedings{bb158240,
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#TT154110"}
@inproceedings{bb158241,
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#TT154111"}
@inproceedings{bb158242,
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#TT154112"}
@inproceedings{bb158243,
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#TT154113"}
@inproceedings{bb158244,
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#TT154114"}
@inproceedings{bb158245,
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#TT154115"}
@inproceedings{bb158246,
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#TT154116"}
@inproceedings{bb158247,
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#TT154117"}
@inproceedings{bb158248,
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#TT154118"}
@inproceedings{bb158249,
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#TT154119"}
@inproceedings{bb158250,
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#TT154120"}
@inproceedings{bb158251,
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#TT154121"}
@inproceedings{bb158252,
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#TT154122"}
@inproceedings{bb158253,
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#TT154123"}
@inproceedings{bb158254,
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#TT154124"}
@inproceedings{bb158255,
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#TT154125"}
@inproceedings{bb158256,
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#TT154126"}
@inproceedings{bb158257,
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#TT154127"}
@inproceedings{bb158258,
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#TT154128"}
@inproceedings{bb158259,
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#TT154129"}
@inproceedings{bb158260,
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#TT154130"}
@inproceedings{bb158261,
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#TT154131"}
@inproceedings{bb158262,
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#TT154132"}
@inproceedings{bb158263,
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#TT154133"}
@inproceedings{bb158264,
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#TT154134"}
@inproceedings{bb158265,
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#TT154135"}
@inproceedings{bb158266,
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#TT154136"}
@inproceedings{bb158267,
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#TT154137"}
@inproceedings{bb158268,
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#TT154138"}
@inproceedings{bb158269,
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#TT154139"}
@inproceedings{bb158270,
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#TT154140"}
@inproceedings{bb158271,
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#TT154141"}
@inproceedings{bb158272,
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#TT154142"}
@inproceedings{bb158273,
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#TT154143"}
@inproceedings{bb158274,
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#TT154144"}
@inproceedings{bb158275,
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#TT154145"}
@inproceedings{bb158276,
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#TT154146"}
@inproceedings{bb158277,
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#TT154147"}
@inproceedings{bb158278,
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#TT154148"}
@inproceedings{bb158279,
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#TT154149"}
@inproceedings{bb158280,
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#TT154150"}
@inproceedings{bb158281,
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#TT154151"}
@inproceedings{bb158282,
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#TT154152"}
@inproceedings{bb158283,
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#TT154153"}
@inproceedings{bb158284,
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#TT154154"}
@inproceedings{bb158285,
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#TT154155"}
@inproceedings{bb158286,
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#TT154156"}
@inproceedings{bb158287,
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#TT154157"}
@inproceedings{bb158288,
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#TT154158"}
@inproceedings{bb158289,
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#TT154159"}
@inproceedings{bb158290,
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#TT154160"}
@inproceedings{bb158291,
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#TT154161"}
@inproceedings{bb158292,
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#TT154162"}
@inproceedings{bb158293,
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#TT154163"}
@inproceedings{bb158294,
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#TT154164"}
@inproceedings{bb158295,
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#TT154165"}
@inproceedings{bb158296,
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#TT154166"}
@inproceedings{bb158297,
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#TT154167"}
@inproceedings{bb158298,
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#TT154168"}
@inproceedings{bb158299,
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#TT154169"}
Last update:May 24, 2026 at 14:46:09