{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"1608.03981","title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","created":"2016-08-13","cited_by_count":1358},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"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":"2102.02808","title":"Multi-Stage Progressive Image Restoration","created":"2021-02-04","cited_by_count":816},{"id":"1802.08797","title":"Residual Dense Network for Image Super-Resolution","created":"2018-02-24","cited_by_count":799},{"id":"2008.13751","title":"Plug-and-Play Image Restoration with Deep Denoiser Prior","created":"2020-08-31","cited_by_count":470},{"id":"1704.03264","title":"Learning Deep CNN Denoiser Prior for Image Restoration","created":"2017-04-11","cited_by_count":408},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1908.03826","title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","created":"2019-08-10","cited_by_count":362},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"2108.05054","title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","created":"2021-08-11","cited_by_count":326},{"id":"2003.06792","title":"Learning Enriched Features for Real Image Restoration and Enhancement","created":"2020-03-15","cited_by_count":312},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"1702.00288","title":"Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)","created":"2017-02-01","cited_by_count":224},{"id":"1812.10477","title":"Residual Dense Network for Image Restoration","created":"2018-12-25","cited_by_count":181},{"id":"2106.16031","title":"ResViT: Residual vision transformers for multi-modal medical image synthesis","created":"2021-06-30","cited_by_count":177},{"id":"1708.00961","title":"Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss","created":"2017-08-03","cited_by_count":162},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"1710.01992","title":"Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks","created":"2017-10-04","cited_by_count":138},{"id":"1610.09736","title":"A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction","created":"2016-10-31","cited_by_count":87},{"id":"1808.04256","title":"CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)","created":"2018-08-10","cited_by_count":82},{"id":"2105.08059","title":"Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers","created":"2021-05-15","cited_by_count":77},{"id":"2203.12621","title":"MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion","created":"2022-03-23","cited_by_count":67},{"id":"1811.03691","title":"Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?","created":"2018-11-08","cited_by_count":54},{"id":"1802.05656","title":"3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network","created":"2018-02-15","cited_by_count":47},{"id":"2108.10772","title":"DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising","created":"2021-08-24","cited_by_count":46},{"id":"2202.13517","title":"CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoising","created":"2022-02-28","cited_by_count":46},{"id":"2203.14186","title":"RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution","created":"2022-03-27","cited_by_count":44},{"id":"2001.00704","title":"SAINT: Spatially Aware Interpolation NeTwork for Medical Slice Synthesis","created":"2020-01-03","cited_by_count":37},{"id":"2110.06178","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","created":"2021-10-12","cited_by_count":36},{"id":"2011.00139","title":"EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising","created":"2020-10-30","cited_by_count":26},{"id":"2106.04650","title":"TED-net: Convolution-free T2T Vision Transformer-based Encoder-decoder Dilation network for Low-dose CT Denoising","created":"2021-06-08","cited_by_count":21},{"id":"1609.04375","title":"A Perspective on Deep Imaging","created":"2016-09-10","cited_by_count":16},{"id":"2104.08538","title":"Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoising","created":"2021-04-17","cited_by_count":15},{"id":"2011.13913","title":"Progressively Volumetrized Deep Generative Models for Data-Efficient Contextual Learning of MR Image Recovery","created":"2020-11-27","cited_by_count":14},{"id":"2011.05684","title":"Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising","created":"2020-11-11","cited_by_count":10},{"id":"2102.05105","title":"Deep learning architectural designs for super-resolution of noisy images","created":"2021-02-09","cited_by_count":5},{"id":"1810.13059","title":"Visual Attention Network for Low Dose CT","created":"2018-10-31","cited_by_count":3},{"id":"2108.06915","title":"End-to-End Adaptive Monte Carlo Denoising and Super-Resolution","created":"2021-08-16","cited_by_count":1}],"next_cursor":null}