{"list":"other","total":72,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"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":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"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":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"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":"1612.02177","title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","created":"2016-12-07","cited_by_count":727},{"id":"2204.04676","title":"Simple Baselines for Image Restoration","created":"2022-04-10","cited_by_count":708},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"1711.07064","title":"DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks","created":"2017-11-19","cited_by_count":367},{"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":"1802.01770","title":"Scale-recurrent Network for Deep Image Deblurring","created":"2018-02-06","cited_by_count":333},{"id":"2108.05054","title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","created":"2021-08-11","cited_by_count":326},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"id":"1904.03468","title":"Deep Stacked Hierarchical Multi-patch Network for Image Deblurring","created":"2019-04-06","cited_by_count":206},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"2004.01860","title":"Deblurring by Realistic Blurring","created":"2020-04-04","cited_by_count":188},{"id":"2001.06816","title":"Human-Aware Motion Deblurring","created":"2020-01-19","cited_by_count":175},{"id":"1908.08207","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","created":"2019-08-22","cited_by_count":171},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142},{"id":"2005.00305","title":"Defocus Deblurring Using Dual-Pixel Data","created":"2020-05-01","cited_by_count":139},{"id":"2004.05343","title":"Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring","created":"2020-04-11","cited_by_count":119},{"id":"1911.07410","title":"Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training","created":"2019-11-18","cited_by_count":112},{"id":"2108.13610","title":"Iterative Filter Adaptive Network for Single Image Defocus Deblurring","created":"2021-08-31","cited_by_count":86},{"id":"2108.08617","title":"Spatially-Adaptive Image Restoration using Distortion-Guided Networks","created":"2021-08-19","cited_by_count":77},{"id":"2112.04491","title":"Improving Image Restoration by Revisiting Global Information Aggregation","created":"2021-12-08","cited_by_count":61},{"id":"2108.09108","title":"Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions","created":"2021-08-20","cited_by_count":54},{"id":"2204.00367","title":"Learning to Deblur using Light Field Generated and Real Defocus Images","created":"2022-04-01","cited_by_count":46},{"id":"2012.03255","title":"Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data","created":"2020-12-06","cited_by_count":42},{"id":"2202.09652","title":"MSSNet: Multi-Scale-Stage Network for Single Image Deblurring","created":"2022-02-19","cited_by_count":31},{"id":"1605.06885","title":"Bridging Category-level and Instance-level Semantic Image Segmentation","created":"2016-05-23","cited_by_count":21},{"id":"2108.05251","title":"Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning","created":"2021-08-11","cited_by_count":20},{"id":"2111.00454","title":"Gaussian Kernel Mixture Network for Single Image Defocus Deblurring","created":"2021-10-31","cited_by_count":20},{"id":"1804.08181","title":"Large Receptive Field Networks for High-Scale Image Super-Resolution","created":"2018-04-22","cited_by_count":5}],"next_cursor":null}