{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249},{"id":"1605.01710","title":"Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications","created":"2016-05-05","cited_by_count":246},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170},{"id":"2012.14214","title":"TransPose: Keypoint Localization via Transformer","created":"2020-12-28","cited_by_count":126},{"id":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121},{"id":"2108.03032","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","created":"2021-08-06","cited_by_count":116},{"id":"2111.07910","title":"Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction","created":"2021-11-15","cited_by_count":110},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"1807.07837","title":"Rank Minimization for Snapshot Compressive Imaging","created":"2018-07-20","cited_by_count":99},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"2103.06104","title":"U-Net Transformer: Self and Cross Attention for Medical Image Segmentation","created":"2021-03-10","cited_by_count":81},{"id":"2003.13654","title":"Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging","created":"2020-03-30","cited_by_count":78},{"id":"2204.07908","title":"MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction","created":"2022-04-17","cited_by_count":72},{"id":"2203.04845","title":"Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction","created":"2022-03-09","cited_by_count":67},{"id":"2203.02149","title":"HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging","created":"2022-03-04","cited_by_count":66},{"id":"2003.04030","title":"Learning Delicate Local Representations for Multi-Person Pose Estimation","created":"2020-03-09","cited_by_count":65},{"id":"2103.07152","title":"Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging","created":"2021-03-12","cited_by_count":58},{"id":"1302.2575","title":"Coded aperture compressive temporal imaging","created":"2013-02-04","cited_by_count":57},{"id":"2012.08364","title":"GAP-net for Snapshot Compressive Imaging","created":"2020-12-13","cited_by_count":54},{"id":"2201.01893","title":"Flow-Guided Sparse Transformer for Video Deblurring","created":"2022-01-06","cited_by_count":43},{"id":"2101.04822","title":"Plug-and-Play Algorithms for Video Snapshot Compressive Imaging","created":"2021-01-13","cited_by_count":42},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"id":"2108.12654","title":"Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging","created":"2021-08-28","cited_by_count":35},{"id":"2107.02133","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","created":"2021-07-05","cited_by_count":33},{"id":"2204.02844","title":"Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training","created":"2022-04-06","cited_by_count":29},{"id":"2112.06238","title":"HerosNet: Hyperspectral Explicable Reconstruction and Optimal Sampling Deep Network for Snapshot Compressive Imaging","created":"2021-12-12","cited_by_count":26},{"id":"2201.00466","title":"RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark","created":"2022-01-03","cited_by_count":24},{"id":"1502.06260","title":"Compressive Hyperspectral Imaging with Side Information","created":"2015-02-22","cited_by_count":19},{"id":"1707.03553","title":"Aerial Vehicle Tracking by Adaptive Fusion of Hyperspectral Likelihood Maps","created":"2017-07-12","cited_by_count":13},{"id":"1608.03440","title":"Recurrent Neural Networks to Correct Satellite Image Classification Maps","created":"2016-08-11","cited_by_count":4}],"next_cursor":null}