@inproceedings{bb161600,
AUTHOR = "Chen, M.Z. and Lin, M. and Lin, Z.H. and Zhang, Y.X. and Chao, F. and Ji, R.R.",
TITLE = "SMMix: Self-Motivated Image Mixing for Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "17214-17224",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157454"}
@inproceedings{bb161601,
AUTHOR = "Kim, D. and Angelova, A. and Kuo, W.C.",
TITLE = "Contrastive Feature Masking Open-Vocabulary Vision Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15556-15566",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157455"}
@inproceedings{bb161602,
AUTHOR = "Li, Z.K. and Gu, Q.Y.",
TITLE = "I-ViT: Integer-only Quantization for Efficient Vision Transformer
Inference",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "17019-17029",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157456"}
@inproceedings{bb161603,
AUTHOR = "Frumkin, N. and Gope, D. and Marculescu, D.",
TITLE = "Jumping through Local Minima: Quantization in the Loss Landscape of
Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "16932-16942",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157457"}
@inproceedings{bb161604,
AUTHOR = "Li, Z.K. and Xiao, J.R. and Yang, L.W. and Gu, Q.Y.",
TITLE = "RepQ-ViT: Scale Reparameterization for Post-Training Quantization of
Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "17181-17190",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157458"}
@inproceedings{bb161605,
AUTHOR = "Wang, X. and Chu, X.J. and Han, C. and Zhang, X.Y.",
TITLE = "SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs
and Transformers",
BOOKTITLE = NIVT23,
YEAR = "2023",
PAGES = "731-741",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157459"}
@inproceedings{bb161606,
AUTHOR = "Chen, Y.H. and Weng, Y.C. and Kao, C.H. and Chien, C. and Chiu, W.C. and Peng, W.H.",
TITLE = "TransTIC: Transferring Transformer-based Image Compression from Human
Perception to Machine Perception",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "23240-23250",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157460"}
@inproceedings{bb161607,
AUTHOR = "Li, Y.Y. and Hu, J. and Wen, Y. and Evangelidis, G. and Salahi, K. and Wang, Y.Z. and Tulyakov, S. and Ren, J.",
TITLE = "Rethinking Vision Transformers for MobileNet Size and Speed",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "16843-16854",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157461"}
@inproceedings{bb161608,
AUTHOR = "Nurgazin, M. and Tu, N.A.",
TITLE = "A Comparative Study of Vision Transformer Encoders and Few-shot
Learning for Medical Image Classification",
BOOKTITLE = CVAMD23,
YEAR = "2023",
PAGES = "2505-2513",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157462"}
@inproceedings{bb161609,
AUTHOR = "Vasu, P.K.A. and Gabriel, J. and Zhu, J. and Tuzel, O. and Ranjan, A.",
TITLE = "FastViT: A Fast Hybrid Vision Transformer using Structural
Reparameterization",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5762-5772",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157463"}
@inproceedings{bb161610,
AUTHOR = "Tang, C. and Zhang, L.L. and Jiang, H.Q. and Xu, J.H. and Cao, T. and Zhang, Q. and Yang, Y.Q. and Wang, Z. and Yang, M.",
TITLE = "ElasticViT: Conflict-aware Supernet Training for Deploying Fast
Vision Transformer on Diverse Mobile Devices",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5806-5817",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157464"}
@inproceedings{bb161611,
AUTHOR = "Lin, W.F. and Wu, Z.H. and Chen, J.Y. and Huang, J. and Jin, L.W.",
TITLE = "Scale-Aware Modulation Meet Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5992-6003",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157465"}
@inproceedings{bb161612,
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#TT157466"}
@inproceedings{bb161613,
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#TT157467"}
@inproceedings{bb161614,
AUTHOR = "Wang, Z.Q. and Fang, Y.T. and Cao, J.H. and Zhang, Q. and Wang, Z.R. and Xu, R.",
TITLE = "Masked Spiking Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "1761-1771",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157468"}
@inproceedings{bb161615,
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#TT157469"}
@inproceedings{bb161616,
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#TT157470"}
@inproceedings{bb161617,
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#TT157471"}
@inproceedings{bb161618,
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#TT157472"}
@inproceedings{bb161619,
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#TT157473"}
@inproceedings{bb161620,
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#TT157474"}
@inproceedings{bb161621,
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#TT157475"}
@inproceedings{bb161622,
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#TT157476"}
@inproceedings{bb161623,
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#TT157477"}
@inproceedings{bb161624,
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#TT157478"}
@inproceedings{bb161625,
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#TT157479"}
@inproceedings{bb161626,
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#TT157480"}
@inproceedings{bb161627,
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#TT157481"}
@inproceedings{bb161628,
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#TT157482"}
@inproceedings{bb161629,
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#TT157483"}
@inproceedings{bb161630,
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#TT157484"}
@inproceedings{bb161631,
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#TT157485"}
@inproceedings{bb161632,
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#TT157486"}
@inproceedings{bb161633,
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#TT157487"}
@inproceedings{bb161634,
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#TT157488"}
@inproceedings{bb161635,
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#TT157489"}
@inproceedings{bb161636,
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#TT157490"}
@inproceedings{bb161637,
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#TT157491"}
@inproceedings{bb161638,
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#TT157492"}
@inproceedings{bb161639,
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#TT157493"}
@inproceedings{bb161640,
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#TT157494"}
@inproceedings{bb161641,
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#TT157495"}
@inproceedings{bb161642,
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#TT157496"}
@inproceedings{bb161643,
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#TT157497"}
@inproceedings{bb161644,
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#TT157498"}
@inproceedings{bb161645,
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#TT157499"}
@inproceedings{bb161646,
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#TT157500"}
@inproceedings{bb161647,
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#TT157501"}
@inproceedings{bb161648,
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#TT157502"}
@inproceedings{bb161649,
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#TT157503"}
@inproceedings{bb161650,
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#TT157504"}
@inproceedings{bb161651,
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#TT157505"}
@inproceedings{bb161652,
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#TT157506"}
@inproceedings{bb161653,
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#TT157507"}
@inproceedings{bb161654,
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#TT157508"}
@inproceedings{bb161655,
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#TT157509"}
@inproceedings{bb161656,
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#TT157510"}
@inproceedings{bb161657,
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#TT157511"}
@inproceedings{bb161658,
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#TT157512"}
@inproceedings{bb161659,
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#TT157513"}
@inproceedings{bb161660,
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#TT157514"}
@inproceedings{bb161661,
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#TT157515"}
@inproceedings{bb161662,
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#TT157516"}
@inproceedings{bb161663,
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#TT157517"}
@inproceedings{bb161664,
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#TT157518"}
@inproceedings{bb161665,
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#TT157519"}
@inproceedings{bb161666,
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#TT157520"}
@inproceedings{bb161667,
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#TT157521"}
@inproceedings{bb161668,
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#TT157522"}
@inproceedings{bb161669,
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#TT157523"}
@inproceedings{bb161670,
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#TT157524"}
@inproceedings{bb161671,
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#TT157525"}
@inproceedings{bb161672,
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#TT157526"}
@inproceedings{bb161673,
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#TT157527"}
@inproceedings{bb161674,
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#TT157528"}
@inproceedings{bb161675,
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#TT157529"}
@inproceedings{bb161676,
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#TT157530"}
@inproceedings{bb161677,
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#TT157531"}
@inproceedings{bb161678,
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#TT157532"}
@inproceedings{bb161679,
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#TT157533"}
@inproceedings{bb161680,
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#TT157534"}
@inproceedings{bb161681,
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#TT157535"}
@inproceedings{bb161682,
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#TT157536"}
@inproceedings{bb161683,
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#TT157537"}
@inproceedings{bb161684,
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#TT157538"}
@inproceedings{bb161685,
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#TT157539"}
@inproceedings{bb161686,
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#TT157540"}
@inproceedings{bb161687,
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#TT157541"}
@inproceedings{bb161688,
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#TT157542"}
@inproceedings{bb161689,
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#TT157543"}
@inproceedings{bb161690,
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#TT157544"}
@inproceedings{bb161691,
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#TT157545"}
@inproceedings{bb161692,
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#TT157546"}
@inproceedings{bb161693,
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#TT157547"}
@inproceedings{bb161694,
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#TT157548"}
@inproceedings{bb161695,
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#TT157549"}
@inproceedings{bb161696,
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#TT157550"}
@inproceedings{bb161697,
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#TT157551"}
@inproceedings{bb161698,
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#TT157552"}
@inproceedings{bb161699,
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#TT157553"}
Last update:Oct 8, 2026 at 11:03:09