@inproceedings{bb140100,
        AUTHOR = "Qiu, Y. and Yamamoto, S. and Nakashima, K. and Suzuki, R. and Iwata, K. and Kataoka, H. and Satoh, Y.",
        TITLE = "Describing and Localizing Multiple Changes with Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1951-1960",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136105"}

@inproceedings{bb140101,
        AUTHOR = "Song, M. and Choi, J. and Han, B.H.",
        TITLE = "Variable-Rate Deep Image Compression through Spatially-Adaptive
Feature Transform",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2360-2369",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136106"}

@inproceedings{bb140102,
        AUTHOR = "Shenga, H. and Cai, S. and Liu, Y. and Deng, B. and Huang, J.Q. and Hua, X.S. and Zhao, M.J.",
        TITLE = "Improving 3D Object Detection with Channel-wise Transformer",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2723-2732",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136107"}

@inproceedings{bb140103,
        AUTHOR = "Zhang, P.C. and Dai, X. and Yang, J.W. and Xiao, B. and Yuan, L. and Zhang, L. and Gao, J.F.",
        TITLE = "Multi-Scale Vision Longformer: A New Vision Transformer for
High-Resolution Image Encoding",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2978-2988",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136108"}

@inproceedings{bb140104,
        AUTHOR = "Dong, Q. and Tu, Z.W. and Liao, H. and Zhang, Y.T. and Mahadevan, V. and Soatto, S.",
        TITLE = "Visual Relationship Detection Using Part-and-Sum Transformers with
Composite Queries",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "3530-3539",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136109"}

@inproceedings{bb140105,
        AUTHOR = "Fan, H.Q. and Xiong, B. and Mangalam, K. and Li, Y. and Yan, Z.C. and Malik, J. and Feichtenhofer, C.",
        TITLE = "Multiscale Vision Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "6804-6815",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136110"}

@inproceedings{bb140106,
        AUTHOR = "Mahmood, K. and Mahmood, R. and van Dijk, M.",
        TITLE = "On the Robustness of Vision Transformers to Adversarial Examples",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "7818-7827",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136111"}

@inproceedings{bb140107,
        AUTHOR = "Chen, X.L. and Xie, S. and He, K.",
        TITLE = "An Empirical Study of Training Self-Supervised Vision Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "9620-9629",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136112"}

@inproceedings{bb140108,
        AUTHOR = "Yuan, Y. and Weng, X. and Ou, Y. and Kitani, K.",
        TITLE = "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent
Forecasting",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "9793-9803",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136113"}

@inproceedings{bb140109,
        AUTHOR = "Wu, K. and Peng, H.W. and Chen, M.H. and Fu, J.L. and Chao, H.Y.",
        TITLE = "Rethinking and Improving Relative Position Encoding for Vision
Transformer",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "10013-10021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136114"}

@inproceedings{bb140110,
        AUTHOR = "Bhojanapalli, S. and Chakrabarti, A. and Glasner, D. and Li, D. and Unterthiner, T. and Veit, A.",
        TITLE = "Understanding Robustness of Transformers for Image Classification",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "10211-10221",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136115"}

@inproceedings{bb140111,
        AUTHOR = "Yan, B. and Peng, H. and Fu, J.L. and Wang, D. and Lu, H.C.",
        TITLE = "Learning Spatio-Temporal Transformer for Visual Tracking",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "10428-10437",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136116"}

@inproceedings{bb140112,
        AUTHOR = "Heo, B. and Yun, S. and Han, D.Y. and Chun, S. and Choe, J. and Oh, S.J.",
        TITLE = "Rethinking Spatial Dimensions of Vision Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "11916-11925",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136117"}

@inproceedings{bb140113,
        AUTHOR = "Voskou, A. and Panousis, K.P. and Kosmopoulos, D. and Metaxas, D.N. and Chatzis, S.",
        TITLE = "Stochastic Transformer Networks with Linear Competing Units:
Application to end-to-end SL Translation",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "11926-11935",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136118"}

@inproceedings{bb140114,
        AUTHOR = "Ranftl, R. and Bochkovskiy, A. and Koltun, V.",
        TITLE = "Vision Transformers for Dense Prediction",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "12159-12168",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136119"}

@inproceedings{bb140115,
        AUTHOR = "Chen, M.H. and Peng, H.W. and Fu, J.L. and Ling, H.B.",
        TITLE = "AutoFormer: Searching Transformers for Visual Recognition",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "12250-12260",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136120"}

@inproceedings{bb140116,
        AUTHOR = "Yuan, K. and Guo, S.P. and Liu, Z.W. and Zhou, A. and Yu, F.W. and Wu, W.",
        TITLE = "Incorporating Convolution Designs into Visual Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "559-568",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136121"}

@inproceedings{bb140117,
        AUTHOR = "Chen, Z. and Xie, L.X. and Niu, J.W. and Liu, X.F. and Wei, L. and Tian, Q.",
        TITLE = "Visformer: The Vision-friendly Transformer",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "569-578",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136122"}

@inproceedings{bb140118,
        AUTHOR = "Yao, Z.L. and Cao, Y. and Lin, Y.T. and Liu, Z. and Zhang, Z. and Hu, H.",
        TITLE = "Leveraging Batch Normalization for Vision Transformers",
        BOOKTITLE = NeruArch21,
        YEAR = "2021",
        PAGES = "413-422",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136123"}

@inproceedings{bb140119,
        AUTHOR = "Graham, B. and El Nouby, A. and Touvron, H. and Stock, P. and Joulin, A. and Jegou, H. and Douze, M.",
        TITLE = "LeViT: a Vision Transformer in ConvNet's Clothing for Faster
Inference",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "12239-12249",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136124"}

@inproceedings{bb140120,
        AUTHOR = "Horvath, J. and Baireddy, S. and Hao, H.X. and Montserrat, D.M. and Delp, E.J.",
        TITLE = "Manipulation Detection in Satellite Images Using Vision Transformer",
        BOOKTITLE = WMF21,
        YEAR = "2021",
        PAGES = "1032-1041",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136125"}

@inproceedings{bb140121,
        AUTHOR = "Horvath, J. and Montserrat, D.M. and Hao, H.X. and Delp, E.J.",
        TITLE = "Manipulation Detection in Satellite Images Using Deep Belief Networks",
        BOOKTITLE = WMF20,
        YEAR = "2020",
        PAGES = "2832-2840",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136126"}

@inproceedings{bb140122,
        AUTHOR = "Beal, J. and Wu, H.Y. and Park, D.H. and Zhai, A. and Kislyuk, D.",
        TITLE = "Billion-Scale Pretraining with Vision Transformers for Multi-Task
Visual Representations",
        BOOKTITLE = WACV22,
        YEAR = "2022",
        PAGES = "1431-1440",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT136127"}

@article{bb140123,
        AUTHOR = "Hu, H.Q. and Lu, X.F. and Zhang, X.P. and Zhang, T.X. and Sun, G.L.",
        TITLE = "Inheritance Attention Matrix-Based Universal Adversarial
Perturbations on Vision Transformers",
        JOURNAL = SPLetters,
        VOLUME = "28",
        YEAR = "2021",
        PAGES = "1923-1927",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136128"}

@article{bb140124,
        AUTHOR = "Xue, Z.X. and Tan, X. and Yu, X. and Liu, B. and Yu, A. and Zhang, P.Q.",
        TITLE = "Deep Hierarchical Vision Transformer for Hyperspectral and LiDAR Data
Classification",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "3095-3110",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136129"}

@article{bb140125,
        AUTHOR = "Heo, J. and Wang, Y. and Park, J.",
        TITLE = "Occlusion-aware spatial attention transformer for occluded object
recognition",
        JOURNAL = PRL,
        VOLUME = "159",
        YEAR = "2022",
        PAGES = "70-76",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136130"}

@article{bb140126,
        AUTHOR = "Yu, X.H. and Wang, J. and Zhao, Y. and Gao, Y.S.",
        TITLE = "Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained
visual categorization",
        JOURNAL = PR,
        VOLUME = "135",
        YEAR = "2023",
        PAGES = "109131",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136131"}

@article{bb140127,
        AUTHOR = "Wu, G. and Zheng, W.S. and Lu, Y.T. and Tian, Q.",
        TITLE = "PSLT: A Light-Weight Vision Transformer With Ladder Self-Attention
and Progressive Shift",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "11120-11135",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136132"}

@article{bb140128,
        AUTHOR = "Li, K.C. and Wang, Y. and Zhang, J.H. and Gao, P. and Song, G. and Liu, Y. and Li, H.S. and Qiao, Y.",
        TITLE = "UniFormer: Unifying Convolution and Self-Attention for Visual
Recognition",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "12581-12600",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136133"}

@article{bb140129,
        AUTHOR = "Li, H.L. and Xue, M.Q. and Song, J. and Zhang, H.F. and Huang, W.Q. and Liang, L. and Song, M.L.",
        TITLE = "Constituent Attention for Vision Transformers",
        JOURNAL = CVIU,
        VOLUME = "237",
        YEAR = "2023",
        PAGES = "103838",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136134"}

@article{bb140130,
        AUTHOR = "Qin, R. and Wang, C.Z. and Wu, Y.M. and Du, H. and Lv, M.Y.",
        TITLE = "A U-Shaped Convolution-Aided Transformer with Double Attention for
Hyperspectral Image Classification",
        JOURNAL = RS,
        VOLUME = "16",
        YEAR = "2024",
        NUMBER = "2",
        PAGES = "288",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136135"}

@inproceedings{bb140131,
        AUTHOR = "Cai, H. and Li, J. and Hu, M. and Gan, C. and Han, S.",
        TITLE = "EfficientViT: Lightweight Multi-Scale Attention for High-Resolution
Dense Prediction",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "17256-17267",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136136"}

@inproceedings{bb140132,
        AUTHOR = "Ryu, J. and Han, D.Y. and Lim, J.W.",
        TITLE = "Gramian Attention Heads are Strong yet Efficient Vision Learners",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "5818-5828",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136137"}

@inproceedings{bb140133,
        AUTHOR = "Xu, R.H. and Zhang, H. and Hu, W.Z. and Zhang, S.L. and Wang, X.Y.",
        TITLE = "ParCNetV2: Oversized Kernel with Enhanced Attention*",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "5729-5739",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136138"}

@inproceedings{bb140134,
        AUTHOR = "Zhao, B.Y. and Yu, Z. and Lan, S.Y. and Cheng, Y. and Anandkumar, A. and Lao, Y.J. and Alvarez, J.M.",
        TITLE = "Fully Attentional Networks with Self-emerging Token Labeling",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "5562-5572",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136139"}

@inproceedings{bb140135,
        AUTHOR = "Guo, Y. and Stutz, D. and Schiele, B.",
        TITLE = "Robustifying Token Attention for Vision Transformers",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "17511-17522",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136140"}

@inproceedings{bb140136,
        AUTHOR = "Zhao, Y. and Tang, H.D. and Jiang, Y.Y. and A, Y. and Wu, Q. and Wang, J.",
        TITLE = "Parameter-Efficient Vision Transformer with Linear Attention",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "1275-1279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136141"}

@inproceedings{bb140137,
        AUTHOR = "Shi, L. and Huang, H.D. and Song, B. and Tan, M. and Zhao, W.Z. and Xia, T. and Ren, P.J.",
        TITLE = "TAQ: Top-K Attention-Aware Quantization for Vision Transformers",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "1750-1754",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136142"}

@inproceedings{bb140138,
        AUTHOR = "Baili, N. and Frigui, H.",
        TITLE = "ADA-VIT: Attention-Guided Data Augmentation for Vision Transformers",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "385-389",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136143"}

@inproceedings{bb140139,
        AUTHOR = "Ding, M.Y. and Shen, Y. and Fan, L.J. and Chen, Z.F. and Chen, Z. and Luo, P. and Tenenbaum, J. and Gan, C.",
        TITLE = "Visual Dependency Transformers:
Dependency Tree Emerges from Reversed Attention",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "14528-14539",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136144"}

@inproceedings{bb140140,
        AUTHOR = "Song, J.C. and Mou, C. and Wang, S.Q. and Ma, S.W. and Zhang, J.",
        TITLE = "Optimization-Inspired Cross-Attention Transformer for Compressive
Sensing",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "6174-6184",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136145"}

@inproceedings{bb140141,
        AUTHOR = "Hassani, A. and Walton, S. and Li, J.C. and Li, S. and Shi, H.",
        TITLE = "Neighborhood Attention Transformer",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "6185-6194",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136146"}

@inproceedings{bb140142,
        AUTHOR = "Liu, Z.J. and Yang, X.Y. and Tang, H.T. and Yang, S. and Han, S.",
        TITLE = "FlatFormer: Flattened Window Attention for Efficient Point Cloud
Transformer",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "1200-1211",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136147"}

@inproceedings{bb140143,
        AUTHOR = "Pan, X. and Ye, T.Z. and Xia, Z.F. and Song, S. and Huang, G.",
        TITLE = "Slide-Transformer: Hierarchical Vision Transformer with Local
Self-Attention",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "2082-2091",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136148"}

@inproceedings{bb140144,
        AUTHOR = "Zhu, L. and Wang, X.J. and Ke, Z.H. and Zhang, W. and Lau, R.",
        TITLE = "BiFormer: Vision Transformer with Bi-Level Routing Attention",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "10323-10333",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136149"}

@inproceedings{bb140145,
        AUTHOR = "Long, S. and Zhao, Z. and Pi, J. and Wang, S.S. and Wang, J.D.",
        TITLE = "Beyond Attentive Tokens: Incorporating Token Importance and Diversity
for Efficient Vision Transformers",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "10334-10343",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136150"}

@inproceedings{bb140146,
        AUTHOR = "Liu, X.Y. and Peng, H. and Zheng, N.X. and Yang, Y.Q. and Hu, H. and Yuan, Y.X.",
        TITLE = "EfficientViT: Memory Efficient Vision Transformer with Cascaded Group
Attention",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "14420-14430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136151"}

@inproceedings{bb140147,
        AUTHOR = "You, H.R. and Xiong, Y. and Dai, X.L. and Wu, B. and Zhang, P.Z. and Fan, H.Q. and Vajda, P. and Lin, Y.Y.C.",
        TITLE = "Castling-ViT: Compressing Self-Attention via Switching Towards
Linear-Angular Attention at Vision Transformer Inference",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "14431-14442",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136152"}

@inproceedings{bb140148,
        AUTHOR = "Grainger, R. and Paniagua, T. and Song, X. and Cuntoor, N. and Lee, M.W. and Wu, T.F.",
        TITLE = "PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "18568-18578",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136153"}

@inproceedings{bb140149,
        AUTHOR = "Wei, C. and Duke, B. and Jiang, R. and Aarabi, P. and Taylor, G.W. and Shkurti, F.",
        TITLE = "Sparsifiner: Learning Sparse Instance-Dependent Attention for
Efficient Vision Transformers",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "22680-22689",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136154"}

@inproceedings{bb140150,
        AUTHOR = "Bhattacharyya, M. and Chattopadhyay, S. and Nag, S.",
        TITLE = "DeCAtt: Efficient Vision Transformers with Decorrelated Attention
Heads",
        BOOKTITLE = ECV23,
        YEAR = "2023",
        PAGES = "4695-4699",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136155"}

@inproceedings{bb140151,
        AUTHOR = "Tatsunami, Y. and Taki, M.",
        TITLE = "RaftMLP: How Much Can Be Done Without Attention and with Less Spatial
Locality?",
        BOOKTITLE = ACCV22,
        YEAR = "2022",
        PAGES = "VI:459-475",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136156"}

@inproceedings{bb140152,
        AUTHOR = "Bolya, D. and Fu, C.Y. and Dai, X.L. and Zhang, P.Z. and Hoffman, J.",
        TITLE = "Hydra Attention: Efficient Attention with Many Heads",
        BOOKTITLE = CADK22,
        YEAR = "2022",
        PAGES = "35-49",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136157"}

@inproceedings{bb140153,
        AUTHOR = "Chen, X.Y. and Hu, Q. and Li, K. and Zhong, C. and Wang, G.H.",
        TITLE = "Accumulated Trivial Attention Matters in Vision Transformers on Small
Datasets",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "3973-3981",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136158"}

@inproceedings{bb140154,
        AUTHOR = "Lan, H. and Wang, X. and Shen, H. and Liang, P. and Wei, X.",
        TITLE = "Couplformer: Rethinking Vision Transformer with Coupling Attention",
        BOOKTITLE = WACV23,
        YEAR = "2023",
        PAGES = "6464-6473",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136159"}

@inproceedings{bb140155,
        AUTHOR = "Debnath, B. and Po, O. and Chowdhury, F.A. and Chakradhar, S.",
        TITLE = "Cosine Similarity based Few-Shot Video Classifier with
Attention-based Aggregation",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "1273-1279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136160"}

@inproceedings{bb140156,
        AUTHOR = "Mari, C.R. and Gonzalez, D.V. and Bou Balust, E.",
        TITLE = "Multi-Scale Transformer-Based Feature Combination for Image Retrieval",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "3166-3170",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136161"}

@inproceedings{bb140157,
        AUTHOR = "Furukawa, R. and Hotta, K.",
        TITLE = "Local Embedding for Axial Attention",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "2586-2590",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136162"}

@inproceedings{bb140158,
        AUTHOR = "Kakogeorgiou, I. and Gidaris, S. and Psomas, B. and Avrithis, Y. and Bursuc, A. and Karantzalos, K. and Komodakis, N.",
        TITLE = "What to Hide from Your Students: Attention-Guided Masked Image Modeling",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXX:300-318",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136163"}

@inproceedings{bb140159,
        AUTHOR = "Ding, M.Y. and Xiao, B. and Codella, N. and Luo, P. and Wang, J.D. and Yuan, L.",
        TITLE = "DaViT: Dual Attention Vision Transformers",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXIV:74-92",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136164"}

@inproceedings{bb140160,
        AUTHOR = "Wang, P.C. and Wang, X. and Wang, F. and Lin, M. and Chang, S.N. and Li, H. and Jin, R.",
        TITLE = "KVT: k-NN Attention for Boosting Vision Transformers",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXIV:285-302",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136165"}

@inproceedings{bb140161,
        AUTHOR = "Rao, Y.M. and Zhao, W.L. and Zhou, J. and Lu, J.W.",
        TITLE = "AMixer:
Adaptive Weight Mixing for Self-Attention Free Vision Transformers",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXI:50-67",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136166"}

@inproceedings{bb140162,
        AUTHOR = "Li, A. and Jiao, J. and Li, N. and Qi, W. and Xu, W. and Pang, M.",
        TITLE = "Conmw Transformer: A General Vision Transformer Backbone With
Merged-Window Attention",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "1551-1555",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136167"}

@inproceedings{bb140163,
        AUTHOR = "Zhang, Q.M. and Xu, Y.F. and Zhang, J. and Tao, D.C.",
        TITLE = "VSA: Learning Varied-Size Window Attention in Vision Transformers",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXV:466-483",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136168"}

@inproceedings{bb140164,
        AUTHOR = "Mallick, R. and Benois Pineau, J. and Zemmari, A.",
        TITLE = "I Saw: A Self-Attention Weighted Method for Explanation of Visual
Transformers",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "3271-3275",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136169"}

@inproceedings{bb140165,
        AUTHOR = "Song, Z.K. and Yu, J.Q. and Chen, Y.P.P. and Yang, W.",
        TITLE = "Transformer Tracking with Cyclic Shifting Window Attention",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "8781-8790",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136170"}

@inproceedings{bb140166,
        AUTHOR = "Yang, C.L. and Wang, Y.L. and Zhang, J.M. and Zhang, H. and Wei, Z.J. and Lin, Z. and Yuille, A.L.",
        TITLE = "Lite Vision Transformer with Enhanced Self-Attention",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "11988-11998",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136171"}

@inproceedings{bb140167,
        AUTHOR = "Xia, Z.F. and Pan, X. and Song, S. and Li, L.E. and Huang, G.",
        TITLE = "Vision Transformer with Deformable Attention",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "4784-4793",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136172"}

@inproceedings{bb140168,
        AUTHOR = "Yu, T. and Khalitov, R. and Cheng, L. and Yang, Z.R.",
        TITLE = "Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better
than Dot-Product Self-Attention",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "681-690",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136173"}

@inproceedings{bb140169,
        AUTHOR = "Cheng, B. and Misra, I. and Schwing, A.G. and Kirillov, A. and Girdhar, R.",
        TITLE = "Masked-attention Mask Transformer for Universal Image Segmentation",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "1280-1289",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136174"}

@inproceedings{bb140170,
        AUTHOR = "Rangrej, S.B. and Srinidhi, C.L. and Clark, J.J.",
        TITLE = "Consistency driven Sequential Transformers Attention Model for
Partially Observable Scenes",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "2508-2517",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136175"}

@inproceedings{bb140171,
        AUTHOR = "Chen, C.F.R. and Fan, Q.F. and Panda, R.",
        TITLE = "CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image
Classification",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "347-356",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136176"}

@inproceedings{bb140172,
        AUTHOR = "Chefer, H. and Gur, S. and Wolf, L.B.",
        TITLE = "Generic Attention-model Explainability for Interpreting Bi-Modal and
Encoder-Decoder Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "387-396",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136177"}

@inproceedings{bb140173,
        AUTHOR = "Xu, W.J. and Xu, Y.F. and Chang, T. and Tu, Z.W.",
        TITLE = "Co-Scale Conv-Attentional Image Transformers",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "9961-9970",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136178"}

@inproceedings{bb140174,
        AUTHOR = "Yang, G.L. and Tang, H. and Ding, M.L. and Sebe, N. and Ricci, E.",
        TITLE = "Transformer-Based Attention Networks for Continuous Pixel-Wise
Prediction",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "16249-16259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136179"}

@inproceedings{bb140175,
        AUTHOR = "Kim, K. and Wu, B.C. and Dai, X.L. and Zhang, P.Z. and Yan, Z.C. and Vajda, P. and Kim, S.",
        TITLE = "Rethinking the Self-Attention in Vision Transformers",
        BOOKTITLE = ECV21,
        YEAR = "2021",
        PAGES = "3065-3069",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651atvit4.html#TT136180"}

@article{bb140176,
        AUTHOR = "Selva, J. and Johansen, A.S. and Escalera, S. and Nasrollahi, K. and Moeslund, T.B. and Clapes, A.",
        TITLE = "Video Transformers: A Survey",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "12922-12943",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136181"}

@article{bb140177,
        AUTHOR = "Zhang, Z.C. and Chen, Z.D. and Wang, Y.X. and Luo, X. and Xu, X.S.",
        TITLE = "A vision transformer for fine-grained classification by reducing
noise and enhancing discriminative information",
        JOURNAL = PR,
        VOLUME = "145",
        YEAR = "2024",
        PAGES = "109979",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136182"}

@article{bb140178,
        AUTHOR = "Xian, K. and Peng, J. and Cao, Z.G. and Zhang, J.M. and Lin, G.S.",
        TITLE = "ViTA: Video Transformer Adaptor for Robust Video Depth Estimation",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "3302-3316",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136183"}

@inproceedings{bb140179,
        AUTHOR = "Piergiovanni, A. and Kuo, W.C. and Angelova, A.",
        TITLE = "Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video
Learning",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "2214-2224",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136184"}

@inproceedings{bb140180,
        AUTHOR = "Park, J. and Lee, J.Y. and Sohn, K.H.",
        TITLE = "Dual-Path Adaptation from Image to Video Transformers",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "2203-2213",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136185"}

@inproceedings{bb140181,
        AUTHOR = "Karim, R. and Zhao, H. and Wildes, R.P. and Siam, M.",
        TITLE = "MED-VT: Multiscale Encoder-Decoder Video Transformer with Application
to Object Segmentation",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "6323-6333",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136186"}

@inproceedings{bb140182,
        AUTHOR = "Yu, L.J. and Cheng, Y. and Sohn, K. and Lezama, J. and Zhang, H. and Chang, H. and Hauptmann, A.G. and Yang, M.H. and Hao, Y. and Essa, I. and Jiang, L.",
        TITLE = "MAGVIT: Masked Generative Video Transformer",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "10459-10469",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136187"}

@inproceedings{bb140183,
        AUTHOR = "Xing, Z. and Dai, Q. and Hu, H. and Chen, J.J. and Wu, Z. and Jiang, Y.G.",
        TITLE = "SVFormer: Semi-supervised Video Transformer for Action Recognition",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "18816-18826",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136188"}

@inproceedings{bb140184,
        AUTHOR = "Xie, F. and Chu, L. and Li, J.H. and Lu, Y. and Ma, C.",
        TITLE = "VideoTrack: Learning to Track Objects via Video Transformer",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "22826-22835",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136189"}

@inproceedings{bb140185,
        AUTHOR = "Qiu, Z.W. and Yang, Q.S. and Wang, J. and Feng, H.C. and Han, J.Y. and Ding, E. and Xu, C. and Fu, D.M. and Wang, J.D.",
        TITLE = "PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation with
Progressive Video Transformers",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "21254-21263",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136190"}

@inproceedings{bb140186,
        AUTHOR = "Yang, J. and Chen, J.W. and Yanai, K.",
        TITLE = "Transformer-based Cross-modal Recipe Embeddings with Large Batch
Training",
        BOOKTITLE = MMMod23,
        YEAR = "2023",
        PAGES = "II: 471-482",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136191"}

@inproceedings{bb140187,
        AUTHOR = "Huang, K.W. and Chen, G.C.F. and Chang, P.W. and Lin, S.C. and Hsu, C. and Thengane, V. and Lin, J.Y.Y.",
        TITLE = "Strong Gravitational Lensing Parameter Estimation with Vision
Transformer",
        BOOKTITLE = AI4Space22,
        YEAR = "2022",
        PAGES = "143-153",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136192"}

@inproceedings{bb140188,
        AUTHOR = "Zheng, M. and Luo, J.P.",
        TITLE = "Space-time Video Super-resolution 3d Transformer",
        BOOKTITLE = MMMod23,
        YEAR = "2023",
        PAGES = "II: 374-385",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136193"}

@inproceedings{bb140189,
        AUTHOR = "Ye, X. and Bilodeau, G.A.",
        TITLE = "VPTR: Efficient Transformers for Video Prediction",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "3492-3499",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136194"}

@inproceedings{bb140190,
        AUTHOR = "Liang, Y.X. and Zhou, P. and Zimmermann, R. and Yan, S.C.",
        TITLE = "DualFormer:
Local-Global Stratified Transformer for Efficient Video Recognition",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXIV:577-595",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136195"}

@inproceedings{bb140191,
        AUTHOR = "Wang, J. and Yang, X.T. and Li, H.D. and Liu, L. and Wu, Z.X. and Jiang, Y.G.",
        TITLE = "Efficient Video Transformers with Spatial-Temporal Token Selection",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXV:69-86",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136196"}

@inproceedings{bb140192,
        AUTHOR = "Yuan, J. and Barmpoutis, P. and Stathaki, T.",
        TITLE = "Multi-Scale Deformable Transformer Encoder Based Single-Stage
Pedestrian Detection",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "2906-2910",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136197"}

@inproceedings{bb140193,
        AUTHOR = "Yun, H. and Lee, S. and Kim, G.",
        TITLE = "Panoramic Vision Transformer for Saliency Detection in 360 Videos",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXV:422-439",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136198"}

@inproceedings{bb140194,
        AUTHOR = "Sun, G.X. and Hua, Y. and Hu, G.S. and Robertson, N.",
        TITLE = "TDViT: Temporal Dilated Video Transformer for Dense Video Tasks",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXV:285-301",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136199"}

@inproceedings{bb140195,
        AUTHOR = "Wang, Y.H. and Zhang, J.C. and Li, Z.G. and Zeng, X. and Zhang, Z. and Zhang, D. and Long, Y. and Wang, N.",
        TITLE = "Neural Network-based In-Loop Filter for CLIC 2022",
        BOOKTITLE = CLIC22,
        YEAR = "2022",
        PAGES = "1773-1776",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136200"}

@inproceedings{bb140196,
        AUTHOR = "Chang, H.W. and Zhang, H. and Jiang, L. and Liu, C. and Freeman, W.T.",
        TITLE = "MaskGIT: Masked Generative Image Transformer",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "11305-11315",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136201"}

@inproceedings{bb140197,
        AUTHOR = "Herzig, R. and Ben Avraham, E. and Mangalam, K. and Bar, A. and Chechik, G. and Rohrbach, A. and Darrell, T.J. and Globerson, A.",
        TITLE = "Object-Region Video Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "3138-3149",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136202"}

@inproceedings{bb140198,
        AUTHOR = "Wang, R. and Chen, D.D. and Wu, Z. and Chen, Y.P. and Dai, X. and Liu, M.C. and Jiang, Y.G. and Zhou, L. and Yuan, L.",
        TITLE = "BEVT: BERT Pretraining of Video Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "14713-14723",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136203"}

@inproceedings{bb140199,
        AUTHOR = "Wu, C.Y. and Li, Y. and Mangalam, K. and Fan, H.Q. and Xiong, B. and Malik, J. and Feichtenhofer, C.",
        TITLE = "MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient
Long-Term Video Recognition",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "13577-13587",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT136204"}

Last update:Apr 10, 2024 at 09:54:40