@inproceedings{bb151000,
AUTHOR = "He, Y.F. and Lou, Z.Y. and Zhang, L. and Liu, J. and Wu, W.J. and Zhou, H. and Zhuang, B.",
TITLE = "BiViT: Extremely Compressed Binary Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5628-5640",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146928"}
@inproceedings{bb151001,
AUTHOR = "Dutson, M. and Li, Y. and Gupta, M.",
TITLE = "Eventful Transformers:
Leveraging Temporal Redundancy in Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "16865-16877",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146929"}
@inproceedings{bb151002,
AUTHOR = "Wang, Z.Q. and Fang, Y.T. and Cao, J.H. and Zhang, Q. and Wang, Z. and Xu, R.",
TITLE = "Masked Spiking Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "1761-1771",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146930"}
@inproceedings{bb151003,
AUTHOR = "Peebles, W. and Xie, S.",
TITLE = "Scalable Diffusion Models with Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "4172-4182",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146931"}
@inproceedings{bb151004,
AUTHOR = "Mentzer, F. and Agustson, E. and Tschannen, M.",
TITLE = "M2T: Masking Transformers Twice for Faster Decoding",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5317-5326",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146932"}
@inproceedings{bb151005,
AUTHOR = "Xiao, H. and Zheng, W.Z. and Zhu, Z. and Zhou, J. and Lu, J.W.",
TITLE = "Token-Label Alignment for Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5472-5481",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146933"}
@inproceedings{bb151006,
AUTHOR = "Yu, R.Y. and Wang, Z.N. and Wang, Y.H. and Li, K. and Liu, C. and Duan, H.Y. and Ji, X.Y. and Chen, J.",
TITLE = "LaPE: Layer-adaptive Position Embedding for Vision Transformers with
Independent Layer Normalization",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5863-5873",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146934"}
@inproceedings{bb151007,
AUTHOR = "Roy, A. and Verma, V.K. and Voonna, S. and Ghosh, K. and Ghosh, S. and Das, A.",
TITLE = "Exemplar-Free Continual Transformer with Convolutions",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5874-5884",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146935"}
@inproceedings{bb151008,
AUTHOR = "Xu, Y.X. and Li, C. and Li, D. and Sheng, X. and Jiang, F. and Tian, L. and Sirasao, A.",
TITLE = "FDViT: Improve the Hierarchical Architecture of Vision Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5927-5937",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146936"}
@inproceedings{bb151009,
AUTHOR = "Chen, Y.J. and Liu, H.M. and Yin, H.R. and Fan, B.",
TITLE = "Building Vision Transformers with Hierarchy Aware Feature Aggregation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5885-5895",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146937"}
@inproceedings{bb151010,
AUTHOR = "Quetu, V. and Milovanovic, M. and Tartaglione, E.",
TITLE = "Sparse Double Descent in Vision Transformers: Real or Phantom Threat?",
BOOKTITLE = CIAP23,
YEAR = "2023",
PAGES = "II:490-502",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146938"}
@inproceedings{bb151011,
AUTHOR = "Ak, K.E. and Lee, G.G. and Xu, Y. and Shen, M.W.",
TITLE = "Leveraging Efficient Training and Feature Fusion in Transformers for
Multimodal Classification",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1420-1424",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146939"}
@inproceedings{bb151012,
AUTHOR = "Popovic, N. and Paudel, D.P. and Probst, T. and Van Gool, L.J.",
TITLE = "Token-Consistent Dropout For Calibrated Vision Transformers",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1030-1034",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146940"}
@inproceedings{bb151013,
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#TT146941"}
@inproceedings{bb151014,
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#TT146942"}
@inproceedings{bb151015,
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#TT146943"}
@inproceedings{bb151016,
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#TT146944"}
@inproceedings{bb151017,
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#TT146945"}
@inproceedings{bb151018,
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#TT146946"}
@inproceedings{bb151019,
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#TT146947"}
@inproceedings{bb151020,
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#TT146948"}
@inproceedings{bb151021,
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#TT146949"}
@inproceedings{bb151022,
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#TT146950"}
@inproceedings{bb151023,
AUTHOR = "Wei, S.Y. and Ye, T.Z. and Zhang, S. and Tang, Y. and Liang, J.J.",
TITLE = "Joint Token Pruning and Squeezing Towards More Aggressive Compression
of Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2092-2101",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146951"}
@inproceedings{bb151024,
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#TT146952"}
@inproceedings{bb151025,
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#TT146953"}
@inproceedings{bb151026,
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#TT146954"}
@inproceedings{bb151027,
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#TT146955"}
@inproceedings{bb151028,
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#TT146956"}
@inproceedings{bb151029,
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#TT146957"}
@inproceedings{bb151030,
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#TT146958"}
@inproceedings{bb151031,
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#TT146959"}
@inproceedings{bb151032,
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#TT146960"}
@inproceedings{bb151033,
AUTHOR = "Zhang, J.P. and Huang, Y.Z. and Wu, W.B. and Lyu, M.R.",
TITLE = "Transferable Adversarial Attacks on Vision Transformers with Token
Gradient Regularization",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "16415-16424",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT146961"}
@inproceedings{bb151034,
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#TT146962"}
@inproceedings{bb151035,
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#TT146963"}
@inproceedings{bb151036,
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#TT146964"}
@inproceedings{bb151037,
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#TT146965"}
@inproceedings{bb151038,
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#TT146966"}
@inproceedings{bb151039,
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#TT146967"}
@inproceedings{bb151040,
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#TT146968"}
@inproceedings{bb151041,
AUTHOR = "Li, B. and Hu, Y. 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#TT146969"}
@inproceedings{bb151042,
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#TT146970"}
@inproceedings{bb151043,
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#TT146971"}
@inproceedings{bb151044,
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#TT146972"}
@inproceedings{bb151045,
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#TT146973"}
@inproceedings{bb151046,
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#TT146974"}
@inproceedings{bb151047,
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#TT146975"}
@inproceedings{bb151048,
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#TT146976"}
@inproceedings{bb151049,
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#TT146977"}
@inproceedings{bb151050,
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#TT146978"}
@inproceedings{bb151051,
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#TT146979"}
@inproceedings{bb151052,
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#TT146980"}
@inproceedings{bb151053,
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#TT146981"}
@inproceedings{bb151054,
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#TT146982"}
@inproceedings{bb151055,
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#TT146983"}
@inproceedings{bb151056,
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#TT146984"}
@inproceedings{bb151057,
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#TT146985"}
@inproceedings{bb151058,
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#TT146986"}
@inproceedings{bb151059,
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#TT146987"}
@inproceedings{bb151060,
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#TT146988"}
@inproceedings{bb151061,
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#TT146989"}
@inproceedings{bb151062,
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#TT146990"}
@inproceedings{bb151063,
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#TT146991"}
@inproceedings{bb151064,
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#TT146992"}
@inproceedings{bb151065,
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#TT146993"}
@inproceedings{bb151066,
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#TT146994"}
@inproceedings{bb151067,
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#TT146995"}
@inproceedings{bb151068,
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#TT146996"}
@inproceedings{bb151069,
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#TT146997"}
@inproceedings{bb151070,
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#TT146998"}
@inproceedings{bb151071,
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#TT146999"}
@inproceedings{bb151072,
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#TT147000"}
@inproceedings{bb151073,
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#TT147001"}
@inproceedings{bb151074,
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#TT147002"}
@inproceedings{bb151075,
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#TT147003"}
@inproceedings{bb151076,
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#TT147004"}
@inproceedings{bb151077,
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#TT147005"}
@inproceedings{bb151078,
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#TT147006"}
@inproceedings{bb151079,
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#TT147007"}
@inproceedings{bb151080,
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#TT147008"}
@inproceedings{bb151081,
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#TT147009"}
@inproceedings{bb151082,
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#TT147010"}
@inproceedings{bb151083,
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#TT147011"}
@inproceedings{bb151084,
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#TT147012"}
@inproceedings{bb151085,
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#TT147013"}
@inproceedings{bb151086,
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#TT147014"}
@inproceedings{bb151087,
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#TT147015"}
@inproceedings{bb151088,
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#TT147016"}
@inproceedings{bb151089,
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#TT147017"}
@inproceedings{bb151090,
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#TT147018"}
@inproceedings{bb151091,
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#TT147019"}
@inproceedings{bb151092,
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#TT147020"}
@inproceedings{bb151093,
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#TT147021"}
@inproceedings{bb151094,
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#TT147022"}
@inproceedings{bb151095,
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#TT147023"}
@inproceedings{bb151096,
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#TT147024"}
@inproceedings{bb151097,
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#TT147025"}
@inproceedings{bb151098,
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#TT147026"}
@inproceedings{bb151099,
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#TT147027"}
Last update:Jun 18, 2025 at 15:22:01