@inproceedings{bb154200,
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#TT150122"}
@inproceedings{bb154201,
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#TT150123"}
@inproceedings{bb154202,
AUTHOR = "Chen, X.Y. and Hu, Q.H. 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#TT150124"}
@inproceedings{bb154203,
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#TT150125"}
@inproceedings{bb154204,
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#TT150126"}
@inproceedings{bb154205,
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#TT150127"}
@inproceedings{bb154206,
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#TT150128"}
@inproceedings{bb154207,
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#TT150129"}
@inproceedings{bb154208,
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#TT150130"}
@inproceedings{bb154209,
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#TT150131"}
@inproceedings{bb154210,
AUTHOR = "Li, A. and Jiao, J.C. 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#TT150132"}
@inproceedings{bb154211,
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#TT150133"}
@inproceedings{bb154212,
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#TT150134"}
@inproceedings{bb154213,
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#TT150135"}
@inproceedings{bb154214,
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#TT150136"}
@inproceedings{bb154215,
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#TT150137"}
@inproceedings{bb154216,
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#TT150138"}
@inproceedings{bb154217,
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#TT150139"}
@inproceedings{bb154218,
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#TT150140"}
@inproceedings{bb154219,
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#TT150141"}
@inproceedings{bb154220,
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#TT150142"}
@inproceedings{bb154221,
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#TT150143"}
@inproceedings{bb154222,
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#TT150144"}
@inproceedings{bb154223,
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#TT150145"}
@article{bb154224,
AUTHOR = "Yang, J.H. and Li, X.Y. and Zheng, M. and Wang, Z.H. and Zhu, Y.Q. and Guo, X.Q. and Yuan, Y.C. and Chai, Z. and Jiang, S.Q.",
TITLE = "MemBridge: Video-Language Pre-Training With Memory-Augmented
Inter-Modality Bridge",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "4073-4087",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150146"}
@article{bb154225,
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#TT150147"}
@article{bb154226,
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#TT150148"}
@article{bb154227,
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#TT150149"}
@article{bb154228,
AUTHOR = "Zhang, J.S. and Gu, L.F. and Lai, Y.K. and Wang, X.Y. and Li, K.",
TITLE = "Toward Grouping in Large Scenes With Occlusion-Aware Spatio-Temporal
Transformers",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "3919-3929",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150150"}
@inproceedings{bb154229,
AUTHOR = "Goyal, R. and Fan, W.C. and Siam, M. and Sigal, L.",
TITLE = "TAM-VT: Transformation-Aware Multi-Scale Video Transformer for
Segmentation and Tracking",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8336-8345",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150151"}
@inproceedings{bb154230,
AUTHOR = "Wu, R. and Zhou, F.X. and Yin, Z.W. and Liu, K.J.",
TITLE = "Aligning Neuronal Coding of Dynamic Visual Scenes with Foundation
Vision Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXVIII: 238-254",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150152"}
@inproceedings{bb154231,
AUTHOR = "Lu, Y.W. and Liu, D.F. and Wang, Q.F. and Han, C. and Cui, Y.M. and Cao, Z.W. and Zhang, X.L. and Chen, Y.J.V. and Fan, H.",
TITLE = "ProMotion: Prototypes as Motion Learners",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28109-28119",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150153"}
@inproceedings{bb154232,
AUTHOR = "Choi, J. and Lee, S. and Chu, J.W. and Choi, M. and Kim, H.W.J.",
TITLE = "vid-TLDR: Training Free Token merging for Light-Weight Video
Transformer",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18771-18781",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150154"}
@inproceedings{bb154233,
AUTHOR = "Kowal, M. and Dave, A. and Ambrus, R. and Gaidon, A. and Derpanis, K.G. and Tokmakov, P.",
TITLE = "Understanding Video Transformers via Universal Concept Discovery",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "10946-10956",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150155"}
@inproceedings{bb154234,
AUTHOR = "Herzig, R. and Abramovich, O. and Ben Avraham, E. and Arbelle, A. and Karlinsky, L. and Shamir, A. and Darrell, T.J. and Globerson, A.",
TITLE = "PromptonomyViT: Multi-Task Prompt Learning Improves Video
Transformers using Synthetic Scene Data",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6789-6801",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150156"}
@inproceedings{bb154235,
AUTHOR = "Li, K.C. and Wang, Y. and Li, Y.Z. and Wang, Y. and He, Y. and Wang, L.M. and Qiao, Y.",
TITLE = "Unmasked Teacher: Towards Training-Efficient Video Foundation Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "19891-19903",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150157"}
@inproceedings{bb154236,
AUTHOR = "Ko, D. and Choi, J. and Choi, H.K. and On, K.W. and Roh, B. and Kim, H.W.J.",
TITLE = "MELTR: Meta Loss Transformer for Learning to Fine-tune Video
Foundation Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "20105-20115",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150158"}
@inproceedings{bb154237,
AUTHOR = "Piergiovanni, A.J. 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#TT150159"}
@inproceedings{bb154238,
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#TT150160"}
@inproceedings{bb154239,
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#TT150161"}
@inproceedings{bb154240,
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#TT150162"}
@inproceedings{bb154241,
AUTHOR = "Xing, Z. and Dai, Q. and Hu, H. and Chen, J.J. and Wu, Z.X. 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#TT150163"}
@inproceedings{bb154242,
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#TT150164"}
@inproceedings{bb154243,
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#TT150165"}
@inproceedings{bb154244,
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#TT150166"}
@inproceedings{bb154245,
AUTHOR = "Li, Y. and Min, K. and Tripathi, S. and Vasconcelos, N.M.",
TITLE = "SViTT: Temporal Learning of Sparse Video-Text Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18919-18929",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150167"}
@inproceedings{bb154246,
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#TT150168"}
@inproceedings{bb154247,
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#TT150169"}
@inproceedings{bb154248,
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#TT150170"}
@inproceedings{bb154249,
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#TT150171"}
@inproceedings{bb154250,
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#TT150172"}
@inproceedings{bb154251,
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#TT150173"}
@inproceedings{bb154252,
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#TT150174"}
@inproceedings{bb154253,
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#TT150175"}
@inproceedings{bb154254,
AUTHOR = "Wang, Y.H. and Zhang, J.C. and Li, Z.G. and Zeng, X. and Zhang, Z. and Zhang, D. and Long, Y.L. 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#TT150176"}
@inproceedings{bb154255,
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#TT150177"}
@inproceedings{bb154256,
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#TT150178"}
@inproceedings{bb154257,
AUTHOR = "Wang, R. and Chen, D.D. and Wu, Z.X. 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#TT150179"}
@inproceedings{bb154258,
AUTHOR = "Wu, C.Y. and Li, Y.H. 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#TT150180"}
@inproceedings{bb154259,
AUTHOR = "Mangalam, K. and Fan, H.Q. and Li, Y.H. and Wu, C.Y. and Xiong, B. and Feichtenhofer, C. and Malik, J.",
TITLE = "Reversible Vision Transformers",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10820-10830",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150181"}
@inproceedings{bb154260,
AUTHOR = "Li, Y.H. and Wu, C.Y. and Fan, H.Q. and Mangalam, K. and Xiong, B. and Malik, J. and Feichtenhofer, C.",
TITLE = "MViTv2: Improved Multiscale Vision Transformers for Classification
and Detection",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "4794-4804",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150182"}
@inproceedings{bb154261,
AUTHOR = "Ranasinghe, K. and Naseer, M. and Khan, S. and Khan, F.S. and Ryoo, M.S.",
TITLE = "Self-supervised Video Transformer",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "2864-2874",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150183"}
@inproceedings{bb154262,
AUTHOR = "Yang, S.S. and Wang, X.G. and Li, Y. and Fang, Y.X. and Fang, J. and Liu, W.Y. and Zhao, X. and Shan, Y.",
TITLE = "Temporally Efficient Vision Transformer for Video Instance
Segmentation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "2875-2885",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150184"}
@inproceedings{bb154263,
AUTHOR = "Liu, Z. and Ning, J. and Cao, Y. and Wei, Y.X. and Zhang, Z. and Lin, S. and Hu, H.",
TITLE = "Video Swin Transformer",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3192-3201",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150185"}
@inproceedings{bb154264,
AUTHOR = "Yan, S. and Xiong, X. and Arnab, A. and Lu, Z.C. and Zhang, M. and Sun, C. and Schmid, C.",
TITLE = "Multiview Transformers for Video Recognition",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3323-3333",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150186"}
@inproceedings{bb154265,
AUTHOR = "Shao, R.Z. and Wu, G. and Zhou, Y.M. and Fu, Y. and Fang, L. and Liu, Y.B.",
TITLE = "LocalTrans: A Multiscale Local Transformer Network for
Cross-Resolution Homography Estimation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "14870-14879",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150187"}
@inproceedings{bb154266,
AUTHOR = "Rombach, R. and Esser, P. and Ommer, B.",
TITLE = "Geometry-Free View Synthesis: Transformers and no 3D Priors",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "14336-14346",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150188"}
@inproceedings{bb154267,
AUTHOR = "Tan, J. and Tang, J.Q. and Wang, L.M. and Wu, G.S.",
TITLE = "Relaxed Transformer Decoders for Direct Action Proposal Generation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "13506-13515",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150189"}
@inproceedings{bb154268,
AUTHOR = "Liu, S. and Fan, H.Q. and Qian, S.S. and Chen, Y. and Ding, W. and Wang, Z.Y.",
TITLE = "HiT: Hierarchical Transformer with Momentum Contrast for Video-Text
Retrieval",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "11895-11905",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150190"}
@inproceedings{bb154269,
AUTHOR = "Truong, T.D. and Duong, C.N. and Vu, T.D. and Pham, H.A. and Raj, B. and Le, N. and Luu, K.",
TITLE = "The Right to Talk: An Audio-Visual Transformer Approach",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1085-1094",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150191"}
@inproceedings{bb154270,
AUTHOR = "Weng, W.M. and Zhang, Y.Y. and Xiong, Z.W.",
TITLE = "Event-based Video Reconstruction Using Transformer",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "2543-2552",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150192"}
@inproceedings{bb154271,
AUTHOR = "Arnab, A. and Dehghani, M. and Heigold, G. and Sun, C. and Lucic, M. and Schmid, C.",
TITLE = "ViViT: A Video Vision Transformer",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "6816-6826",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150193"}
@inproceedings{bb154272,
AUTHOR = "Girdhar, R. and Grauman, K.",
TITLE = "Anticipative Video Transformer",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "13485-13495",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150194"}
@inproceedings{bb154273,
AUTHOR = "Zhang, Y. and Li, X.Y. and Liu, C.H. and Shuai, B. and Zhu, Y. and Brattoli, B. and Chen, H. and Marsic, I. and Tighe, J.",
TITLE = "VidTr: Video Transformer Without Convolutions",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "13557-13567",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150195"}
@inproceedings{bb154274,
AUTHOR = "Chen, J.W. and Ho, C.M.",
TITLE = "MM-ViT: Multi-Modal Video Transformer for Compressed Video Action
Recognition",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "786-797",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150196"}
@inproceedings{bb154275,
AUTHOR = "Li, S.Y. and Li, X. and Lu, J.W. and Zhou, J.",
TITLE = "Self-supervised Video Hashing via Bidirectional Transformers",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "13544-13553",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vidt3.html#TT150197"}
@article{bb154276,
AUTHOR = "Iakymchuk, T. and Rosado Munoz, A. and Guerrero Martinez, J. and Bataller Mompean, M. and Frances Villora, J.",
TITLE = "Simplified spiking neural network architecture and STDP learning
algorithm applied to image classification",
JOURNAL = JIVP,
VOLUME = "2015",
YEAR = "2015",
NUMBER = "1",
PAGES = "4",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150198"}
@article{bb154277,
AUTHOR = "Cao, Y.Q. and Chen, Y. and Khosla, D.",
TITLE = "Spiking Deep Convolutional Neural Networks for Energy-Efficient Object
Recognition",
JOURNAL = IJCV,
VOLUME = "113",
YEAR = "2015",
NUMBER = "1",
MONTH = "May",
PAGES = "54-66",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150199"}
@article{bb154278,
AUTHOR = "Saleh, A.Y. and Shamsuddin, S.M. and Hamed, H.N.A.",
TITLE = "A hybrid differential evolution algorithm for parameter tuning of
evolving spiking neural network",
JOURNAL = IJCVR,
VOLUME = "7",
YEAR = "2017",
NUMBER = "1/2",
PAGES = "20-34",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150200"}
@article{bb154279,
AUTHOR = "Falez, P. and Tirilly, P. and Bilasco, I.M. and Devienne, P. and Boulet, P.",
TITLE = "Unsupervised visual feature learning with spike-timing-dependent plasticity:
How far are we from traditional feature learning approaches?",
JOURNAL = PR,
VOLUME = "93",
YEAR = "2019",
PAGES = "418-429",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150201"}
@article{bb154280,
AUTHOR = "Chakraborty, B. and She, X.Y. and Mukhopadhyay, S.",
TITLE = "A Fully Spiking Hybrid Neural Network for Energy-Efficient Object
Detection",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "9014-9029",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150202"}
@article{bb154281,
AUTHOR = "Zhang, Z. and Liu, Q.",
TITLE = "Spike-Event-Driven Deep Spiking Neural Network With Temporal Encoding",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "484-488",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150203"}
@article{bb154282,
AUTHOR = "Chen, J.K. and Qiu, X.L. and Ding, C.B. and Wu, Y.R.",
TITLE = "SAR image classification based on spiking neural network through
spike-time dependent plasticity and gradient descent",
JOURNAL = PandRS,
VOLUME = "188",
YEAR = "2022",
PAGES = "109-124",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150204"}
@article{bb154283,
AUTHOR = "Wu, J. and Xu, C.L. and Han, X. and Zhou, D.Q. and Zhang, M. and Li, H.Z. and Tan, K.C.",
TITLE = "Progressive Tandem Learning for Pattern Recognition With Deep Spiking
Neural Networks",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "11",
MONTH = "November",
PAGES = "7824-7840",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150205"}
@article{bb154284,
AUTHOR = "Chen, X.Y. and Yang, Q. and Wu, J. and Li, H.Z. and Tan, K.C.",
TITLE = "A Hybrid Neural Coding Approach for Pattern Recognition With Spiking
Neural Networks",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "3064-3078",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150206"}
@article{bb154285,
AUTHOR = "Rua, E.A. and van Hamme, T. and Preuveneers, D. and Joosen, W.",
TITLE = "Discriminative training of spiking neural networks organised in
columns for stream-based biometric authentication",
JOURNAL = IET-Bio,
VOLUME = "11",
YEAR = "2022",
NUMBER = "5",
PAGES = "485-497",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150207"}
@article{bb154286,
AUTHOR = "Zhan, Q.G. and Liu, G.S. and Xie, X.R. and Sun, G.L. and Tang, H.J.",
TITLE = "Effective Transfer Learning Algorithm in Spiking Neural Networks",
JOURNAL = Cyber,
VOLUME = "52",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "13323-13335",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150208"}
@article{bb154287,
AUTHOR = "Zhu, L. and Dong, S.W. and Li, J.N. and Huang, T.J. and Tian, Y.H.",
TITLE = "Ultra-High Temporal Resolution Visual Reconstruction From a
Fovea-Like Spike Camera via Spiking Neuron Model",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "1",
MONTH = "January",
PAGES = "1233-1249",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150209"}
@article{bb154288,
AUTHOR = "Guo, Y.F. and Peng, W.H. and Chen, Y.P. and Zhang, L.W. and Liu, X. and Huang, X.H. and Ma, Z.",
TITLE = "Joint A-SNN: Joint training of artificial and spiking neural networks
via self-Distillation and weight factorization",
JOURNAL = PR,
VOLUME = "142",
YEAR = "2023",
PAGES = "109639",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150210"}
@article{bb154289,
AUTHOR = "Yao, M. and Zhao, G.S. and Zhang, H.Y. and Hu, Y.F. and Deng, L. and Tian, Y.H. and Xu, B. and Li, G.Q.",
TITLE = "Attention Spiking Neural Networks",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "8",
MONTH = "August",
PAGES = "9393-9410",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150211"}
@article{bb154290,
AUTHOR = "Yan, Z.L. and Zhou, J. and Wong, W.F.",
TITLE = "CQ+ Training: Minimizing Accuracy Loss in Conversion From
Convolutional Neural Networks to Spiking Neural Networks",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "11600-11611",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150212"}
@article{bb154291,
AUTHOR = "Eshraghian, J.K. and Ward, M. and Neftci, E.O. and Wang, X.X. and Lenz, G. and Dwivedi, G. and Bennamoun, M. and Jeong, D.S. and Lu, W.D.",
TITLE = "Training Spiking Neural Networks Using Lessons From Deep Learning",
JOURNAL = PIEEE,
VOLUME = "111",
YEAR = "2023",
NUMBER = "9",
MONTH = "September",
PAGES = "1016-1054",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150213"}
@article{bb154292,
AUTHOR = "Tang, J.X. and Lai, J.H. and Xie, X.H. and Yang, L.X. and Zheng, W.S.",
TITLE = "AC2AS: Activation Consistency Coupled ANN-SNN framework for fast and
memory-efficient SNN training",
JOURNAL = PR,
VOLUME = "144",
YEAR = "2023",
PAGES = "109826",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150214"}
@article{bb154293,
AUTHOR = "Wang, S. and Peng, Y.X. and Wang, L. and Li, T.",
TITLE = "Boundary-Aware Deformable Spiking Neural Network for Hyperspectral
Image Classification",
JOURNAL = RS,
VOLUME = "15",
YEAR = "2023",
NUMBER = "20",
PAGES = "5020",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150215"}
@article{bb154294,
AUTHOR = "Hu, Y.F. and Zheng, Q. and Jiang, X.D. and Pan, G.",
TITLE = "Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "12",
MONTH = "December",
PAGES = "14546-14562",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150216"}
@article{bb154295,
AUTHOR = "Duan, P.Q. and Ma, Y. and Zhou, X.Y. and Shi, X.Y. and Wang, Z.H.W. and Huang, T.J. and Shi, B.X.",
TITLE = "NeuroZoom: Denoising and Super Resolving Neuromorphic Events and
Spikes",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "12",
MONTH = "December",
PAGES = "15219-15232",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150217"}
@article{bb154296,
AUTHOR = "Jeyasothy, A. and Suresh, S. and Ramasamy, S. and Sundararajan, N.",
TITLE = "Development of a Novel Transformation of Spiking Neural Classifier to
an Interpretable Classifier",
JOURNAL = Cyber,
VOLUME = "54",
YEAR = "2024",
NUMBER = "1",
MONTH = "January",
PAGES = "3-12",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150218"}
@article{bb154297,
AUTHOR = "Yang, F. and Su, L. and Zhao, J.X. and Chen, X. and Wang, X.Y. and Jiang, N. and Hu, Q.",
TITLE = "SA-FlowNet: Event-based self-attention optical flow estimation with
spiking-analogue neural networks",
JOURNAL = IET-CV,
VOLUME = "17",
YEAR = "2023",
NUMBER = "8",
PAGES = "925-935",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150219"}
@article{bb154298,
AUTHOR = "Yang, S.M. and Wang, H.W. and Pang, Y.W. and Jin, Y.C. and Linares Barranco, B.",
TITLE = "Integrating Visual Perception With Decision Making in Neuromorphic
Fault-Tolerant Quadruplet-Spike Learning Framework",
JOURNAL = SMCS,
VOLUME = "54",
YEAR = "2024",
NUMBER = "3",
MONTH = "March",
PAGES = "1502-1514",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150220"}
@article{bb154299,
AUTHOR = "Zhao, R. and Xiong, R.Q. and Zhang, J. and Yu, Z.F. and Zhu, S.Y. and Ma, L. and Huang, T.J.",
TITLE = "Spike Camera Image Reconstruction Using Deep Spiking Neural Networks",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "6",
MONTH = "June",
PAGES = "5207-5212",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651sp1.html#TT150221"}
Last update:Oct 6, 2025 at 14:07:43