{"list":"other","total":56,"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":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1807.02758","title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","created":"2018-07-08","cited_by_count":1264},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"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":"2102.02808","title":"Multi-Stage Progressive Image Restoration","created":"2021-02-04","cited_by_count":816},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"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":"1903.10082","title":"Residual Non-local Attention Networks for Image Restoration","created":"2019-03-24","cited_by_count":236},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2003.07761","title":"CycleISP: Real Image Restoration via Improved Data Synthesis","created":"2020-03-17","cited_by_count":213},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2012.11409","title":"3D Object Detection with Pointformer","created":"2020-12-21","cited_by_count":194},{"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":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2011.14027","title":"General Multi-label Image Classification with Transformers","created":"2020-11-27","cited_by_count":127},{"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":"1807.07837","title":"Rank Minimization for Snapshot Compressive Imaging","created":"2018-07-20","cited_by_count":99},{"id":"2003.13654","title":"Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging","created":"2020-03-30","cited_by_count":78},{"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":"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":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"id":"1708.04208","title":"Learning Blind Motion Deblurring","created":"2017-08-14","cited_by_count":36},{"id":"2107.02133","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","created":"2021-07-05","cited_by_count":33},{"id":"2104.11712","title":"Skeletor: Skeletal Transformers for Robust Body-Pose Estimation","created":"2021-04-23","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":"1909.07229","title":"Global Aggregation then Local Distribution in Fully Convolutional Networks","created":"2019-09-16","cited_by_count":22},{"id":"1707.03553","title":"Aerial Vehicle Tracking by Adaptive Fusion of Hyperspectral Likelihood Maps","created":"2017-07-12","cited_by_count":13},{"id":"2201.05768","title":"Spectral Compressive Imaging Reconstruction Using Convolution and Contextual Transformer","created":"2022-01-15","cited_by_count":4}],"next_cursor":null}