{"list":"other","total":94,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"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":"1807.02758","title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","created":"2018-07-08","cited_by_count":1264},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"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":"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":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"2103.14006","title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","created":"2021-03-25","cited_by_count":529},{"id":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"id":"2008.13751","title":"Plug-and-Play Image Restoration with Deep Denoiser Prior","created":"2020-08-31","cited_by_count":470},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"1809.02165","title":"Deep Learning for Generic Object Detection: A Survey","created":"2018-09-06","cited_by_count":392},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"1802.01770","title":"Scale-recurrent Network for Deep Image Deblurring","created":"2018-02-06","cited_by_count":333},{"id":"1712.00080","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","created":"2017-11-30","cited_by_count":326},{"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":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"1903.10082","title":"Residual Non-local Attention Networks for Image Restoration","created":"2019-03-24","cited_by_count":236},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"1712.06116","title":"Learning a Single Convolutional Super-Resolution Network for Multiple Degradations","created":"2017-12-17","cited_by_count":228},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","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":"1708.01692","title":"Video Frame Interpolation via Adaptive Separable Convolution","created":"2017-08-05","cited_by_count":213},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"1904.03468","title":"Deep Stacked Hierarchical Multi-patch Network for Image Deblurring","created":"2019-04-06","cited_by_count":206},{"id":"2104.00416","title":"Unsupervised Degradation Representation Learning for Blind Super-Resolution","created":"2021-04-01","cited_by_count":177},{"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":"1806.02919","title":"Non-Local Recurrent Network for Image Restoration","created":"2018-06-07","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":"1911.00627","title":"Quadratic video interpolation","created":"2019-11-02","cited_by_count":145},{"id":"1907.10244","title":"AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation","created":"2019-07-24","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":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121},{"id":"2004.05343","title":"Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring","created":"2020-04-11","cited_by_count":119},{"id":"2007.12622","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","created":"2020-07-17","cited_by_count":118},{"id":"2008.00455","title":"Video Super-Resolution with Recurrent Structure-Detail Network","created":"2020-08-02","cited_by_count":116},{"id":"1904.12257","title":"Spatio-Temporal Filter Adaptive Network for Video Deblurring","created":"2019-04-28","cited_by_count":106},{"id":"2012.08512","title":"FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation","created":"2020-12-15","cited_by_count":98},{"id":"2002.11616","title":"Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution","created":"2020-02-26","cited_by_count":91},{"id":"2003.07018","title":"Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution","created":"2020-03-16","cited_by_count":90},{"id":"2007.11803","title":"MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution","created":"2020-07-23","cited_by_count":89},{"id":"2004.02501","title":"Cascaded Deep Video Deblurring Using Temporal Sharpness Prior","created":"2020-04-06","cited_by_count":85},{"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":"2103.15977","title":"Flow-based Kernel Prior with Application to Blind Super-Resolution","created":"2021-03-29","cited_by_count":74},{"id":"2108.05301","title":"Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling","created":"2021-08-11","cited_by_count":73},{"id":"1909.08080","title":"Efficient Video Super-Resolution through Recurrent Latent Space Propagation","created":"2019-09-17","cited_by_count":69},{"id":"2004.03791","title":"Learning A Single Network for Scale-Arbitrary Super-Resolution","created":"2020-04-08","cited_by_count":66},{"id":"1808.08718","title":"Wide Activation for Efficient and Accurate Image Super-Resolution","created":"2018-08-27","cited_by_count":65},{"id":"1804.00533","title":"Adversarial Spatio-Temporal Learning for Video Deblurring","created":"2018-03-28","cited_by_count":60},{"id":"1906.11890","title":"DVDnet: A Fast Network for Deep Video Denoising","created":"2019-06-04","cited_by_count":60},{"id":"1903.05784","title":"Learning Parallax Attention for Stereo Image Super-Resolution","created":"2019-03-14","cited_by_count":56},{"id":"2103.04260","title":"ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring","created":"2021-03-07","cited_by_count":54},{"id":"2104.10642","title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","created":"2021-04-21","cited_by_count":54},{"id":"2108.05302","title":"Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution","created":"2021-08-11","cited_by_count":52},{"id":"2003.13170","title":"Space-Time-Aware Multi-Resolution Video Enhancement","created":"2020-03-30","cited_by_count":49},{"id":"2008.05765","title":"Revisiting Temporal Modeling for Video Super-resolution","created":"2020-08-13","cited_by_count":46},{"id":"2011.15045","title":"Unsupervised Deep Video Denoising","created":"2020-11-30","cited_by_count":44},{"id":"2108.09982","title":"Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes","created":"2021-08-23","cited_by_count":41},{"id":"2001.02129","title":"Deep Video Super-Resolution using HR Optical Flow Estimation","created":"2020-01-06","cited_by_count":40},{"id":"2101.03904","title":"Trear: Transformer-based RGB-D Egocentric Action Recognition","created":"2021-01-05","cited_by_count":39},{"id":"2103.13767","title":"Patch Craft: Video Denoising by Deep Modeling and Patch Matching","created":"2021-03-25","cited_by_count":38},{"id":"2103.05407","title":"Efficient Multi-Stage Video Denoising with Recurrent Spatio-Temporal Fusion","created":"2021-03-09","cited_by_count":36},{"id":"1904.02870","title":"Fast Spatio-Temporal Residual Network for Video Super-Resolution","created":"2019-04-05","cited_by_count":34},{"id":"2103.15683","title":"Omniscient Video Super-Resolution","created":"2021-03-29","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":"2105.05640","title":"FDAN: Flow-guided Deformable Alignment Network for Video Super-Resolution","created":"2021-05-12","cited_by_count":19},{"id":"2109.14335","title":"A Systematic Survey of Deep Learning-based Single-Image Super-Resolution","created":"2021-09-29","cited_by_count":19},{"id":"1912.09028","title":"Scale-wise Convolution for Image Restoration","created":"2019-12-19","cited_by_count":14},{"id":"2003.04279","title":"Restore from Restored: Video Restoration with Pseudo Clean Video","created":"2020-03-09","cited_by_count":11},{"id":"1904.03834","title":"A Statistical Investigation of Long Memory in Language and Music","created":"2019-04-08","cited_by_count":8},{"id":"2010.08919","title":"Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution","created":"2020-10-18","cited_by_count":7}],"next_cursor":null}