{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"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":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"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":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"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":"1612.02177","title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","created":"2016-12-07","cited_by_count":727},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"1808.03314","title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","created":"2018-08-09","cited_by_count":420},{"id":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379},{"id":"1902.06068","title":"Deep Learning for Image Super-resolution: A Survey","created":"2019-02-16","cited_by_count":369},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"2012.02181","title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","created":"2020-12-03","cited_by_count":304},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302},{"id":"2111.14813","title":"TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions","created":"2021-11-29","cited_by_count":244},{"id":"1701.03077","title":"A General and Adaptive Robust Loss Function","created":"2017-01-11","cited_by_count":236},{"id":"1903.10082","title":"Residual Non-local Attention Networks for Image Restoration","created":"2019-03-24","cited_by_count":236},{"id":"1712.06116","title":"Learning a Single Convolutional Super-Resolution Network for Multiple Degradations","created":"2017-12-17","cited_by_count":228},{"id":"1812.02898","title":"TDAN: Temporally Deformable Alignment Network for Video Super-Resolution","created":"2018-12-07","cited_by_count":226},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220},{"id":"2203.04967","title":"UNeXt: MLP-based Rapid Medical Image Segmentation Network","created":"2022-03-09","cited_by_count":185},{"id":"2206.02146","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","created":"2022-06-05","cited_by_count":170},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"1801.04590","title":"Frame-Recurrent Video Super-Resolution","created":"2018-01-14","cited_by_count":160},{"id":"1611.05250","title":"Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation","created":"2016-11-16","cited_by_count":156},{"id":"1704.02738","title":"Detail-revealing Deep Video Super-resolution","created":"2017-04-10","cited_by_count":148},{"id":"1903.10128","title":"Recurrent Back-Projection Network for Video Super-Resolution","created":"2019-03-25","cited_by_count":148},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"2111.12704","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","created":"2021-11-24","cited_by_count":134},{"id":"1907.01361","title":"FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation","created":"2019-07-01","cited_by_count":128},{"id":"2007.12622","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","created":"2020-07-17","cited_by_count":118},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"id":"1904.12257","title":"Spatio-Temporal Filter Adaptive Network for Video Deblurring","created":"2019-04-28","cited_by_count":106},{"id":"2201.10700","title":"Deep Image Deblurring: A Survey","created":"2022-01-26","cited_by_count":94},{"id":"2003.07018","title":"Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution","created":"2020-03-16","cited_by_count":90},{"id":"2004.02501","title":"Cascaded Deep Video Deblurring Using Temporal Sharpness Prior","created":"2020-04-06","cited_by_count":85},{"id":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83},{"id":"2007.10595","title":"Video Super-resolution with Temporal Group Attention","created":"2020-07-21","cited_by_count":81},{"id":"2009.07265","title":"Understanding Deformable Alignment in Video Super-Resolution","created":"2020-09-15","cited_by_count":78},{"id":"2207.08494","title":"Rethinking Alignment in Video Super-Resolution Transformers","created":"2022-07-18","cited_by_count":71},{"id":"2301.03362","title":"Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --","created":"2023-01-09","cited_by_count":71},{"id":"2212.04362","title":"CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution","created":"2022-12-08","cited_by_count":70},{"id":"1909.08080","title":"Efficient Video Super-Resolution through Recurrent Latent Space Propagation","created":"2019-09-17","cited_by_count":69},{"id":"1906.11890","title":"DVDnet: A Fast Network for Deep Video Denoising","created":"2019-06-04","cited_by_count":60},{"id":"2007.12928","title":"Video Super Resolution Based on Deep Learning: A Comprehensive Survey","created":"2020-07-25","cited_by_count":54},{"id":"2204.04668","title":"NAN: Noise-Aware NeRFs for Burst-Denoising","created":"2022-04-10","cited_by_count":48},{"id":"2111.00207","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","created":"2021-10-30","cited_by_count":43},{"id":"2108.09982","title":"Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes","created":"2021-08-23","cited_by_count":41},{"id":"2203.17276","title":"Bringing Old Films Back to Life","created":"2022-03-31","cited_by_count":31},{"id":"2103.15683","title":"Omniscient Video Super-Resolution","created":"2021-03-29","cited_by_count":30},{"id":"2201.10801","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","created":"2022-01-26","cited_by_count":30},{"id":"2104.10781","title":"NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results","created":"2021-04-21","cited_by_count":26},{"id":"2211.11423","title":"Blur Interpolation Transformer for Real-World Motion from Blur","created":"2022-11-21","cited_by_count":25},{"id":"2201.09355","title":"Transformer-based SAR Image Despeckling","created":"2022-01-23","cited_by_count":15},{"id":"1912.09028","title":"Scale-wise Convolution for Image Restoration","created":"2019-12-19","cited_by_count":14},{"id":"2208.02470","title":"Online Video Super-Resolution with Convolutional Kernel Bypass Graft","created":"2022-08-04","cited_by_count":12},{"id":"1810.05052","title":"Deep Learning for Image Denoising: A Survey","created":"2018-10-11","cited_by_count":11},{"id":"2010.10661","title":"Exploring Overcomplete Representations for Single Image Deraining using CNNs","created":"2020-10-20","cited_by_count":11},{"id":"2009.08692","title":"DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement","created":"2020-09-18","cited_by_count":10},{"id":"2207.10765","title":"Towards Interpretable Video Super-Resolution via Alternating Optimization","created":"2022-07-21","cited_by_count":10},{"id":"2206.06292","title":"MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing","created":"2022-06-13","cited_by_count":9},{"id":"2212.11115","title":"What Makes for Good Tokenizers in Vision Transformer?","created":"2022-12-21","cited_by_count":9},{"id":"1907.10128","title":"Blind Deblurring using Deep Learning: A Survey","created":"2019-07-23","cited_by_count":7},{"id":"2203.06841","title":"STDAN: Deformable Attention Network for Space-Time Video Super-Resolution","created":"2022-03-14","cited_by_count":6},{"id":"2205.12634","title":"Real-Time Video Deblurring via Lightweight Motion Compensation","created":"2022-05-25","cited_by_count":3},{"id":"2105.15077","title":"SDNet: mutil-branch for single image deraining using swin","created":"2021-05-31","cited_by_count":2},{"id":"2210.16236","title":"Multi-task Video Enhancement for Dental Interventions","created":"2022-10-25","cited_by_count":2}],"next_cursor":null}