Keith Price Bibliography Bibtex Entry (ANCHOR 161500 URL http://dx.doi.org/10.1109/TMM.2025.3535321 PAGES 3755-3765 YEAR 2025 MONTH NIL BIBSOURCE http://www.visionbib.com/bibliography/pattern651vit2.html#TT157355 VOLUME 27 JOURNAL MultMed AUTHOR Pan, Y.W. and Li, Y. and Yao, T. and Ngo, C.W. and Mei, T. TITLE Stream-ViT: Learning Streamlined Convolutions in Vision Transformer)


@article{bb161500,
        AUTHOR = "Pan, Y.W. and Li, Y. and Yao, T. and Ngo, C.W. and Mei, T.",
        TITLE = "Stream-ViT: Learning Streamlined Convolutions in Vision Transformer",
        JOURNAL = MultMed,
        VOLUME = "27",
        YEAR = "2025",
        PAGES = "3755-3765",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157355"}

@article{bb161501,
        AUTHOR = "Wen, T. and Wang, H. and Wang, L.G.",
        TITLE = "Dual-Branch Spatial-Spectral Transformer with Similarity Propagation
for Hyperspectral Image Classification",
        JOURNAL = RS,
        VOLUME = "17",
        YEAR = "2025",
        NUMBER = "14",
        PAGES = "2386",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157356"}

@article{bb161502,
        AUTHOR = "Yu, C. and Chen, T. and Gan, Z.X.",
        TITLE = "Taylor-Series-Expansion-Based Vision Transformer Models",
        JOURNAL = PAMI,
        VOLUME = "47",
        YEAR = "2025",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "8213-8230",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157357"}

@article{bb161503,
        AUTHOR = "Kong, Z.L. and Xu, D.K. and Li, Z.G. and Dong, P.Y. and Tang, H. and Wang, Y.Z. and Mukherjee, S.",
        TITLE = "AutoViT: Achieving Real-Time Vision Transformers on Mobile via
Latency-aware Coarse-to-Fine Search",
        JOURNAL = IJCV,
        VOLUME = "133",
        YEAR = "2025",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "6170-6186",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157358"}

@article{bb161504,
        AUTHOR = "Tan, C. and Gao, Z.Y. and Li, S.Y. and Li, S.Z.",
        TITLE = "SimVPv2: Towards Simple Yet Powerful Spatiotemporal Predictive
Learning",
        JOURNAL = MultMed,
        VOLUME = "27",
        YEAR = "2025",
        PAGES = "5170-5184",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157359"}

@inproceedings{bb161505,
        AUTHOR = "Tan, C. and Gao, Z.Y. and Wu, L.R. and Xu, Y.J. and Xia, J. and Li, S.Y. and Li, S.Z.",
        TITLE = "Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive
Learning",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "18770-18782",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157360"}

@article{bb161506,
        AUTHOR = "Yang, S. and Hu, C.Y. and Xie, L. and Lee, F.F. and Chen, Q.",
        TITLE = "MG-SSAF: An advanced vision Transformer",
        JOURNAL = JVCIR,
        VOLUME = "112",
        YEAR = "2025",
        PAGES = "104578",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157361"}

@article{bb161507,
        AUTHOR = "Sharma, A.K. and Verma, N.K.",
        TITLE = "A novel vision transformer with selective residual in multihead
self-attention for pattern recognition",
        JOURNAL = PR,
        VOLUME = "172",
        YEAR = "2026",
        PAGES = "112497",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157362"}

@article{bb161508,
        AUTHOR = "Huang, Y.Q. and Ye, P. and Tu, C.J. and Chen, T. and He, T. and Ouyang, W.L.",
        TITLE = "Sparse-to-Dense Training: A Novel Training Scheme to Enhance Vision
Transformers",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "12329-12340",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157363"}

@article{bb161509,
        AUTHOR = "Xu, G. and Huang, W.F. and Jia, W.J. and Li, J. and Gao, G.W. and Qi, G.J.",
        TITLE = "S2AFormer: Strip Self-Attention for Efficient Vision Transformer",
        JOURNAL = IP,
        VOLUME = "34",
        YEAR = "2025",
        PAGES = "8243-8256",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157364"}

@article{bb161510,
        AUTHOR = "Luo, A. and Yuan, K.W.",
        TITLE = "Simple Self-Organizing Map With Vision Transformers",
        JOURNAL = SPLetters,
        VOLUME = "33",
        YEAR = "2026",
        PAGES = "331-335",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157365"}

@article{bb161511,
        AUTHOR = "Li, Q. and He, J. and Guo, T.C. and Gao, X.P. and Bhanu, B.",
        TITLE = "PE-ViT: Parameter-efficient vision transformer with
dimension-adaptive experts and economical attention",
        JOURNAL = PRL,
        VOLUME = "200",
        YEAR = "2026",
        PAGES = "135-141",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157366"}

@article{bb161512,
        AUTHOR = "Wang, A. and Chen, H. and Lin, Z.J. and Zhao, S.C. and Han, J.G. and Ding, G.G.",
        TITLE = "CAIT: Triple-Win Compression Toward High Accuracy, Fast Inference,
and Favorable Transferability for ViTs",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "1373-1389",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157367"}

@inproceedings{bb161513,
        AUTHOR = "Wang, A. and Chen, H. and Lin, Z.J. and Han, J.G. and Ding, G.G.",
        TITLE = "Rep ViT: Revisiting Mobile CNN From ViT Perspective",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "15909-15920",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157368"}

@article{bb161514,
        AUTHOR = "Liu, Z. and Zhu, J.C. and Li, N.N. and Huang, G.",
        TITLE = "Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for
Vision Transformer",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "2123-2136",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157369"}

@article{bb161515,
        AUTHOR = "Chen, X.Y. and Wang, X.T. and Zhang, W.L. and Kong, X.T. and Qiao, Y. and Zhou, J.T. and Dong, C.",
        TITLE = "HAT: Hybrid Attention Transformer for Image Restoration",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "2676-2694",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157370"}

@article{bb161516,
        AUTHOR = "Li, C. and Su, J. and Gao, J.S.",
        TITLE = "BiPAZSL: A bidirectional progressive attention method for zero-shot
learning domain shift mitigation",
        JOURNAL = PR,
        VOLUME = "174",
        YEAR = "2026",
        PAGES = "112959",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157371"}

@article{bb161517,
        AUTHOR = "Zhang, T.F. and Li, L. and Zhou, Y. and Liu, W.T. and Qian, C. and Hwang, J.N. and Ji, X.Y.",
        TITLE = "CAS-ViT: Convolutional Additive Self-Attention Vision Transformers
for Efficient Mobile Applications",
        JOURNAL = IP,
        VOLUME = "35",
        YEAR = "2026",
        PAGES = "1899-1909",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157372"}

@article{bb161518,
        AUTHOR = "Xiao, W.J. and Li, X.Z. and Hu, L. and Hao, Y.X. and Chen, M.",
        TITLE = "DTSNet: Dynamic Transformer Slimming for Efficient Vision Recognition",
        JOURNAL = MultMed,
        VOLUME = "28",
        YEAR = "2026",
        PAGES = "1589-1600",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157373"}

@article{bb161519,
        AUTHOR = "Xu, G. and Hao, J.W. and Luo, Y. and Shen, L. and Hu, H. and Zeng, D.",
        TITLE = "EEformer: Early Exiting for Transformer With Global-Local Exits and
Progressive Fine-Tuning",
        JOURNAL = MultMed,
        VOLUME = "28",
        YEAR = "2026",
        PAGES = "1352-1364",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157374"}

@article{bb161520,
        AUTHOR = "Zhang, Z.W. and Lin, P.X. and Wang, Z.W. and Zhang, Y.Y. and Xu, Z.Q.J.",
        TITLE = "Complexity Control Facilitates Reasoning-Based Compositional
Generalization in Transformers",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "4336-4349",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157375"}

@article{bb161521,
        AUTHOR = "Zhou, W.W. and Zhao, S.J. and Liu, Y.Z. and Li, Y.P.",
        TITLE = "CCTformer: Calibrated Context-Aware Transformer for Correspondence
Pruning",
        JOURNAL = SPLetters,
        VOLUME = "33",
        YEAR = "2026",
        PAGES = "1461-1465",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157376"}

@article{bb161522,
        AUTHOR = "Chen, P.T. and Shen, M.Z. and Ye, P. and Cao, J.J. and Tu, C.J. and Bouganis, C.S. and Ren, Y.",
        TITLE = "Delta-DiT: Accelerating Diffusion Transformers without Training via
Denoising Property Alignment",
        JOURNAL = IJCV,
        VOLUME = "134",
        YEAR = "2026",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "276",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157377"}

@article{bb161523,
        AUTHOR = "Liu, X.Y. and Shi, H. and Xu, Y. and Wang, Z.F.",
        TITLE = "TaQ-DiT: Time-Aware Quantization for Diffusion Transformers",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "6225-6229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157378"}

@article{bb161524,
        AUTHOR = "Li, C.L. and Zhang, J.W. and Lin, S. and Yang, Z.X. and Liang, J.W. and Liang, X.D. and Chang, X.J.",
        TITLE = "Efficient Training of Large Vision Models via Advanced Automated
Progressive Learning",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "8798-8812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157379"}

@inproceedings{bb161525,
        AUTHOR = "Li, C.L. and Zhuang, B. and Wang, G.R. and Liang, X.D. and Chang, X.J. and Yang, Y.",
        TITLE = "Automated Progressive Learning for Efficient Training of Vision
Transformers",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12476-12486",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157380"}

@article{bb161526,
        AUTHOR = "Fan, Q.H. and Huang, H.B. and Chen, M.R. and Liu, H.M. and He, R.",
        TITLE = "Advancing Vision Transformer With Enhanced Spatial Priors",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "9711-9729",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157381"}

@article{bb161527,
        AUTHOR = "Zhang, J. and Wan, Z.F. and Nie, S. and Li, C.Z. and Shan, S.G. and Chen, X.L.",
        TITLE = "BIMM: Brain-Inspired Masked Modeling for Video Representation
Learning",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "10391-10404",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157382"}

@article{bb161528,
        AUTHOR = "Chen, Y. and Liang, Y. and Lin, Z.C.",
        TITLE = "On the Limitations and Capabilities of Position Embeddings for Length
Generalization",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "10844-10855",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157383"}

@article{bb161529,
        AUTHOR = "Prakash V, J. and Antran Vijay S, A. and Mahendhiran, P.D.",
        TITLE = "A stochastic energy-based formulation of attention for robust and
interpretable transformers",
        JOURNAL = PRL,
        VOLUME = "207",
        YEAR = "2026",
        PAGES = "116-122",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157384"}

@article{bb161530,
        AUTHOR = "Ni, F. and Liu, Y. and Dai, S. and Chen, L. and Feng, C.L. and Zhang, F. and Wu, X. and Bo, Y.M.",
        TITLE = "A Vision Transformer with Dynamic Masking and Cross-Modal Semantic
Learning for Remote Sensing Scene Classification",
        JOURNAL = RS,
        VOLUME = "18",
        YEAR = "2026",
        NUMBER = "16",
        PAGES = "2710",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157385"}

@article{bb161531,
        AUTHOR = "Li, H.Y. and Liu, Y.H. and Sun, H.Y. and Cai, D. and Cui, L. and Bi, W. and Zhao, P.L. and Watanabe, T.",
        TITLE = "SeqPE: Transformer With Sequential Position Encoding",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "11952-11963",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157386"}

@inproceedings{bb161532,
        AUTHOR = "Patel, D. and Babazaki, Y. and Nagase, Y. and Melvin, I. and Min, M.R.Q.",
        TITLE = "Distilling Offline Action Detection Models into Real-Time Streaming
Models",
        BOOKTITLE = WACV26,
        YEAR = "2026",
        PAGES = "6205-6214",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157387"}

@inproceedings{bb161533,
        AUTHOR = "Nozawa, Y. and Lin, Y.C. and Nakamura, K. and Ng, Y.",
        TITLE = "Prompt-Guided Attention Head Selection for Focus-Oriented Image
Retrieval",
        BOOKTITLE = PixFM25,
        YEAR = "2025",
        PAGES = "4131-4141",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157388"}

@inproceedings{bb161534,
        AUTHOR = "Abraham, S.J. and Hauenstein, J.D. and Scheirer, W.J.",
        TITLE = "Wavelet-Based Mechanistic Interpretability of Vision Transformers via
Frequency-Aware Ablations",
        BOOKTITLE = InterpVis25,
        YEAR = "2025",
        PAGES = "4830-4834",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157389"}

@inproceedings{bb161535,
        AUTHOR = "Augustin, M. and Sarwar, S.S. and Elhoushi, M. and Li, Y.C. and Zhang, S.Q. and de Salvo, B.",
        TITLE = "PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers",
        BOOKTITLE = MobileAI25,
        YEAR = "2025",
        PAGES = "1858-1868",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157390"}

@inproceedings{bb161536,
        AUTHOR = "Ali, M. and Raza, H. and Gan, J.Q. and Haris, M.",
        TITLE = "Optimising Vision Transformer Performance on Limited Datasets: A
Multi-Gradient Approach",
        BOOKTITLE = "FaDE-TCV25",
        YEAR = "2025",
        PAGES = "693-702",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157391"}

@inproceedings{bb161537,
        AUTHOR = "Echevarrieta Catalan, N. and Ribas Rodriguez, A. and Cedron, F. and Schwartz, O. and Aguiar Pulido, V.",
        TITLE = "Enhancing Vision Transformer Explainability using Artificial
Astrocytes",
        BOOKTITLE = LXCV25,
        YEAR = "2025",
        PAGES = "58-64",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157392"}

@inproceedings{bb161538,
        AUTHOR = "Takatsuki, R. and Joseph, S. and Fujisawa, I. and Kanai, R.",
        TITLE = "Decoding Vision Transformers: The Diffusion Steering Lens",
        BOOKTITLE = InterpVis25,
        YEAR = "2025",
        PAGES = "4819-4824",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157393"}

@inproceedings{bb161539,
        AUTHOR = "He, X. and Quan, Y.H. and Xu, R. and Ji, H.",
        TITLE = "A Universal Scale-Adaptive Deformable Transformer for Image
Restoration across Diverse Artifacts",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "12731-12741",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157394"}

@inproceedings{bb161540,
        AUTHOR = "Fixelle, J.",
        TITLE = "Hypergraph Vision Transformers: Images are More than Nodes, More than
Edges",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "9751-9761",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157395"}

@inproceedings{bb161541,
        AUTHOR = "Ahmed, S. and Arafat, A.A. and Najafi, D. and Mahmood, A. and Rizve, M.N. and Nahian, M.A. and Zhou, R.Y. and Angizi, S. and Rakin, A.S.",
        TITLE = "DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency
of Vision Transformers at the Edge",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "30147-30156",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157396"}

@inproceedings{bb161542,
        AUTHOR = "Wang, Z.Q. and Xia, X.B. and Chen, R. and Yu, D.D. and Wang, C.H. and Gong, M.M. and Liu, T.L.",
        TITLE = "LaVin-DiT: Large Vision Diffusion Transformer",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "20060-20070",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157397"}

@inproceedings{bb161543,
        AUTHOR = "Zhou, Y. and Xu, Q.S. and Cui, J. and Zhou, J. and Zhang, J. and Hong, R.C. and Zhang, H.W.",
        TITLE = "CARE Transformer: Mobile-Friendly Linear Visual Transformer via
Decoupled Dual Interaction",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "20135-20145",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157398"}

@inproceedings{bb161544,
        AUTHOR = "Yu, H. and Jiang, T. and Jia, S. and Yan, S.N. and Liu, S.N. and Qian, H.L. and Li, G.H. and Dong, S.T. and Yuan, C.",
        TITLE = "ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized
by Trainable Commuting Angle Matrices",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "4508-4517",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157399"}

@inproceedings{bb161545,
        AUTHOR = "Chen, G.L. and Fu, T.W. and Chen, H.W. and Teng, W.B. and Xiao, H.Y. and Zhao, Y.J.",
        TITLE = "RDD: Robust Feature Detector and Descriptor using Deformable
Transformer",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "6394-6403",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157400"}

@inproceedings{bb161546,
        AUTHOR = "Pardyl, A. and Kurzejamski, G. and Olszewski, J. and Trzcinski, T. and Zielinski, B.",
        TITLE = "Beyond Grids: Exploring Elastic Input Sampling for Vision
Transformers",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "8536-8545",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157401"}

@inproceedings{bb161547,
        AUTHOR = "Zhong, Y. and Zhou, Y.",
        TITLE = "Rethinking Low-Rank Adaptation in Vision:
Exploring Head-Level Responsiveness across Diverse Tasks",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "7787-7796",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157402"}

@inproceedings{bb161548,
        AUTHOR = "Pipoli, V. and Bolelli, F. and Sarto, S. and Cornia, M. and Baraldi, L. and Grana, C. and Cucchiara, R. and Ficarra, E.",
        TITLE = "Semantically Conditioned Prompts for Visual Recognition Under Missing
Modality Scenarios",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "4968-4977",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157403"}

@inproceedings{bb161549,
        AUTHOR = "Go, J. and Ryu, J.B.",
        TITLE = "Channel Propagation Networks for Refreshable Vision Transformer",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "1353-1362",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157404"}

@inproceedings{bb161550,
        AUTHOR = "Nauen, T.C. and Palacio, S. and Raue, F. and Dengel, A.",
        TITLE = "Which Transformer to Favor: A Comparative Analysis of Efficiency in
Vision Transformers",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "6955-6966",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157405"}

@inproceedings{bb161551,
        AUTHOR = "Tai, Y.S. and Wu, A.Y.A.",
        TITLE = "AMP-ViT: Optimizing Vision Transformer Efficiency with Adaptive
Mixed-Precision Post-Training Quantization",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "6828-6837",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157406"}

@inproceedings{bb161552,
        AUTHOR = "Chen, P.Q. and Yu, L. and Wan, Y. and Zhang, Y.J. and Wang, J. and Zhong, L.H. and Chen, J.D. and Yang, M.",
        TITLE = "Ecomatcher: Efficient Clustering Oriented Matcher for Detector-free
Image Matching",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "LXVIII: 344-360",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157407"}

@inproceedings{bb161553,
        AUTHOR = "Wang, H.Q. and Zhang, T. and Salzmann, M.",
        TITLE = "Sinder: Repairing the Singular Defects of Dinov2",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "VII: 20-35",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157408"}

@inproceedings{bb161554,
        AUTHOR = "Suri, S. and Walmer, M. and Gupta, K. and Shrivastava, A.",
        TITLE = "Lift: A Surprisingly Simple Lightweight Feature Transform for Dense Vit
Descriptors",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "VII: 110-128",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157409"}

@inproceedings{bb161555,
        AUTHOR = "Pan, Z.Z. and Liu, J. and He, H.Y. and Cai, J.F. and Zhuang, B.",
        TITLE = "Stitched VITS are Flexible Vision Backbones",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XLI: 258-274",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157410"}

@inproceedings{bb161556,
        AUTHOR = "Kim, D.H. and Heo, B. and Han, D.Y.",
        TITLE = "Densenets Reloaded: Paradigm Shift Beyond Resnets and VITS",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "III: 395-415",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157411"}

@inproceedings{bb161557,
        AUTHOR = "Zhang, C. and Cheng, J. and Li, Q.X.",
        TITLE = "An Optimal Control View of Lora and Binary Controller Design for Vision
Transformers",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "LIII: 144-160",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157412"}

@inproceedings{bb161558,
        AUTHOR = "Zhang, T. and Bai, J. and Lu, Z. and Lian, D.Z. and Wang, G. and Wang, X.C. and Xia, S.T.",
        TITLE = "Parameter-efficient and Memory-efficient Tuning for Vision Transformer:
A Disentangled Approach",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XLV: 346-363",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157413"}

@inproceedings{bb161559,
        AUTHOR = "Wang, H.Y. and Tang, H. and Jiang, L. and Shi, S.S. and Naeem, M.F. and Li, H.S. and Schiele, B. and Wang, L.W.",
        TITLE = "Git: Towards Generalist Vision Transformer Through Universal Language
Interface",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XXIX: 55-73",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157414"}

@inproceedings{bb161560,
        AUTHOR = "Wu, Z.G.Y. and Chen, J.X. and Zhong, H. and Huang, D. and Wang, Y.H.",
        TITLE = "Adalog: Post-training Quantization for Vision Transformers with
Adaptive Logarithm Quantizer",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XXVII: 411-427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157415"}

@inproceedings{bb161561,
        AUTHOR = "Xiao, H. and Zheng, W.Z. and Zuo, S.C. and Gao, P. and Zhou, J. and Lu, J.W.",
        TITLE = "Spatialformer: Towards Generalizable Vision Transformers with Explicit
Spatial Understanding",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XIII: 37-54",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157416"}

@inproceedings{bb161562,
        AUTHOR = "Heo, B. and Park, S. and Han, D.Y. and Yun, S.",
        TITLE = "Rotary Position Embedding for Vision Transformer",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "X: 289-305",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157417"}

@inproceedings{bb161563,
        AUTHOR = "Bellitto, G. and Sortino, R. and Spadaro, P. and Palazzo, S. and Salanitri, F.P. and Fiameni, G. and Gavves, E. and Spampinato, C.",
        TITLE = "Vito: Vision Transformer Optimization Via Knowledge Distillation On
Decoders",
        BOOKTITLE = ICIP24,
        YEAR = "2024",
        PAGES = "493-499",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157418"}

@inproceedings{bb161564,
        AUTHOR = "Gani, H. and Saadi, N. and Hussein, N. and Nandakumar, K.",
        TITLE = "Multi-Attribute Vision Transformers are Efficient and Robust Learners",
        BOOKTITLE = ICIP24,
        YEAR = "2024",
        PAGES = "766-772",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157419"}

@inproceedings{bb161565,
        AUTHOR = "Cho, J.H. and Krahenbuhl, P.",
        TITLE = "Language-Conditioned Detection Transformer",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "16593-16603",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157420"}

@inproceedings{bb161566,
        AUTHOR = "Lin, S. and Lyu, P. and Liu, D.R. and Tang, T. and Liang, X.D. and Song, A. and Chang, X.J.",
        TITLE = "MLP Can Be a Good Transformer Learner",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "19489-19498",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157421"}

@inproceedings{bb161567,
        AUTHOR = "Weng, H.H. and Huang, D.Q. and Qiao, Y. and Hu, Z. and Lin, C.Y. and Zhang, T. and Chen, C.L.P.",
        TITLE = "Desigen: A Pipeline for Controllable Design Template Generation",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "12721-12732",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157422"}

@inproceedings{bb161568,
        AUTHOR = "Park, S. and Byun, H.R.",
        TITLE = "Fair-VPT: Fair Visual Prompt Tuning for Image Classification",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "12268-12278",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157423"}

@inproceedings{bb161569,
        AUTHOR = "Xu, H.Y. and Xiang, L. and Ye, H.Y. and Yao, D. and Chu, P.Z. and Li, B.C.",
        TITLE = "Permutation Equivariance of Transformers and its Applications",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "5987-5996",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157424"}

@inproceedings{bb161570,
        AUTHOR = "Zhang, Y.Y. and Ding, X.H. and Gong, K.X. and Ge, Y.X. and Shan, Y. and Yue, X.Y.",
        TITLE = "Multimodal Pathway: Improve Transformers with Irrelevant Data from
Other Modalities",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "6108-6117",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157425"}

@inproceedings{bb161571,
        AUTHOR = "Kobayashi, T.",
        TITLE = "Mean-Shift Feature Transformer",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "6047-6056",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157426"}

@inproceedings{bb161572,
        AUTHOR = "Shi, X.Y. and Hao, Z.C. and Yu, Z.F.",
        TITLE = "SpikingResformer: Bridging ResNet and Vision Transformer in Spiking
Neural Networks",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "5610-5619",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157427"}

@inproceedings{bb161573,
        AUTHOR = "Ye, H.C. and Yu, C. and Ye, P. and Xia, R.Q. and Tang, Y.S. and Lu, J.W. and Chen, T. and Zhang, B.",
        TITLE = "Once for Both: Single Stage of Importance and Sparsity Search for
Vision Transformer Compression",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "5578-5588",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157428"}

@inproceedings{bb161574,
        AUTHOR = "Zhang, J. and Herrmann, C. and Hur, J. and Chen, E. and Jampani, V. and Sun, D.Q. and Yang, M.H.",
        TITLE = "Telling Left from Right: Identifying Geometry-Aware Semantic
Correspondence",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "3076-3085",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157429"}

@inproceedings{bb161575,
        AUTHOR = "Huang, N.C. and Chang, C.C. and Lin, W.C. and Taka, E. and Marculescu, D. and Wu, K.C.A.",
        TITLE = "ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer
Acceleration",
        BOOKTITLE = ECV24,
        YEAR = "2024",
        PAGES = "8006-8015",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157430"}

@inproceedings{bb161576,
        AUTHOR = "Devulapally, A. and Khan, M.F.F. and Advani, S. and Narayanan, V.",
        TITLE = "Multi-Modal Fusion of Event and RGB for Monocular Depth Estimation
Using a Unified Transformer-based Architecture",
        BOOKTITLE = MULA24,
        YEAR = "2024",
        PAGES = "2081-2089",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157431"}

@inproceedings{bb161577,
        AUTHOR = "Yang, Z.D. and Li, Z. and Zeng, A.L. and Li, Z.X. and Yuan, C. and Li, Y.",
        TITLE = "ViTKD: Feature-based Knowledge Distillation for Vision Transformers",
        BOOKTITLE = PBDL24,
        YEAR = "2024",
        PAGES = "1379-1388",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157432"}

@inproceedings{bb161578,
        AUTHOR = "Mehri, F. and Baghshah, M.S. and Pilehvar, M.T.",
        TITLE = "LibraGrad: Balancing Gradient Flow for Universally Better Vision
Transformer Attributions",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "67-78",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157433"}

@inproceedings{bb161579,
        AUTHOR = "Mehri, F. and Fayyaz, M. and Baghshah, M.S. and Pilehvar, M.T.",
        TITLE = "SkipPLUS: Skip the First Few Layers to Better Explain Vision
Transformers",
        BOOKTITLE = FaDE-TCV24,
        YEAR = "2024",
        PAGES = "204-215",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157434"}

@inproceedings{bb161580,
        AUTHOR = "Jain, S. and Dutta, T.",
        TITLE = "Towards Understanding and Improving Adversarial Robustness of Vision
Transformers",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "24736-24745",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157435"}

@inproceedings{bb161581,
        AUTHOR = "Yang, S. and Bai, J. and Gao, K. and Yang, Y. and Li, Y.M. and Xia, S.T.",
        TITLE = "Not All Prompts Are Secure: A Switchable Backdoor Attack Against
Pre-trained Vision Transfomers",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "24431-24441",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157436"}

@inproceedings{bb161582,
        AUTHOR = "Steitz, J.M.O. and Roth, S.",
        TITLE = "Adapters Strike Back",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "23449-23459",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157437"}

@inproceedings{bb161583,
        AUTHOR = "Rangwani, H. and Mondal, P. and Mondal, P. and Mishra, M. and Asokan, A.R. and Babu, R.V.",
        TITLE = "DeiT-LT: Distillation Strikes Back for Vision Transformer Training on
Long-Tailed Datasets",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "23396-23406",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157438"}

@inproceedings{bb161584,
        AUTHOR = "Liu, J.Y. and Teshome, W. and Ghimire, S. and Sznaier, M. and Camps, O.",
        TITLE = "Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers*",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "23009-23018",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157439"}

@inproceedings{bb161585,
        AUTHOR = "Kim, M. and Seo, P.H. and Schmid, C. and Cho, M.",
        TITLE = "Learning Correlation Structures for Vision Transformers",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "18941-18951",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157440"}

@inproceedings{bb161586,
        AUTHOR = "Shi, D.",
        TITLE = "TransNeXt: Robust Foveal Visual Perception for Vision Transformers",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "17773-17783",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157441"}

@inproceedings{bb161587,
        AUTHOR = "Agiza, A. and Neseem, M. and Reda, S.",
        TITLE = "MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task
Learning",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "16196-16205",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157442"}

@inproceedings{bb161588,
        AUTHOR = "Dong, W. and Zhang, X. and Chen, B. and Yan, D.W. and Lin, Z.J. and Yan, Q.S. and Wang, P. and Yang, Y.",
        TITLE = "Low-Rank Rescaled Vision Transformer Fine-Tuning:
A Residual Design Approach",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "16101-16110",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157443"}

@inproceedings{bb161589,
        AUTHOR = "Wu, J. and Kang, W.T. and Tang, H. and Hong, Y. and Yan, Y.",
        TITLE = "On the Faithfulness of Vision Transformer Explanations",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "10936-10945",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157444"}

@inproceedings{bb161590,
        AUTHOR = "Navaneet, K.L. and Koohpayegani, S.A. and Sleiman, E. and Pirsiavash, H.",
        TITLE = "SlowFormer: Adversarial Attack on Compute and Energy Consumption of
Efficient Vision Transformers",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "24786-24797",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157445"}

@inproceedings{bb161591,
        AUTHOR = "Koyun, O.C. and Toreyin, B.U.",
        TITLE = "HaLViT: Half of the Weights are Enough",
        BOOKTITLE = LargeVM24,
        YEAR = "2024",
        PAGES = "3669-3678",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157446"}

@inproceedings{bb161592,
        AUTHOR = "Bafghi, R.A. and Harilal, N. and Monteleoni, C. and Raissi, M.",
        TITLE = "Parameter Efficient Fine-tuning of Self-supervised ViTs without
Catastrophic Forgetting",
        BOOKTITLE = LargeVM24,
        YEAR = "2024",
        PAGES = "3679-3684",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157447"}

@inproceedings{bb161593,
        AUTHOR = "Raissi, M. and Monteleoni, C. and Harilal, N. and Bafghi, R.A.",
        TITLE = "Parameter Efficient Fine-tuning of Self-supervised ViTs without
Catastrophic Forgetting",
        BOOKTITLE = LargeVM24,
        YEAR = "2024",
        PAGES = "7864-7869",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157447"}

@inproceedings{bb161594,
        AUTHOR = "Edalati, A. and Hameed, M.G.A. and Mosleh, A.",
        TITLE = "Generalized Kronecker-based Adapters for Parameter-efficient
Fine-tuning of Vision Transformers",
        BOOKTITLE = CRV23,
        YEAR = "2023",
        PAGES = "97-104",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157448"}

@inproceedings{bb161595,
        AUTHOR = "Marouf, I.E. and Tartaglione, E. and Lathuiliere, S.",
        TITLE = "Mini but Mighty: Finetuning ViTs with Mini Adapters",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "1721-1730",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157449"}

@inproceedings{bb161596,
        AUTHOR = "Kim, G. and Kim, J. and Lee, J.S.",
        TITLE = "Exploring Adversarial Robustness of Vision Transformers in the
Spectral Perspective",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "3964-3973",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157450"}

@inproceedings{bb161597,
        AUTHOR = "Han, Q. and Zhang, G.J. and Huang, J.X. and Gao, P. and Wei, Z. and Lu, S.J.",
        TITLE = "Efficient MAE towards Large-Scale Vision Transformers",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "595-604",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157451"}

@inproceedings{bb161598,
        AUTHOR = "Park, J.W. and Kahatapitiya, K. and Kim, D.H. and Sudalairaj, S. and Fan, Q.F. and Ryoo, M.S.",
        TITLE = "Grafting Vision Transformers",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "1134-1143",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157452"}

@inproceedings{bb161599,
        AUTHOR = "Shimizu, S. and Tamaki, T.",
        TITLE = "Joint learning of images and videos with a single Vision Transformer",
        BOOKTITLE = MVA23,
        YEAR = "2023",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT157453"}
Last update:Oct 8, 2026 at 11:03:09