{"list":"other","total":52,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"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":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"1712.04143","title":"Benchmarking Single Image Dehazing and Beyond","created":"2017-12-12","cited_by_count":447},{"id":"1709.05424","title":"NIMA: Neural Image Assessment","created":"2017-09-15","cited_by_count":389},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"1802.01770","title":"Scale-recurrent Network for Deep Image Deblurring","created":"2018-02-06","cited_by_count":333},{"id":"2203.10638","title":"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer","created":"2022-03-20","cited_by_count":320},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"id":"1612.07919","title":"EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis","created":"2016-12-23","cited_by_count":178},{"id":"2304.00451","title":"Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild","created":"2023-04-02","cited_by_count":97},{"id":"1903.08558","title":"Single Image Deraining: A Comprehensive Benchmark Analysis","created":"2019-03-20","cited_by_count":84},{"id":"2210.08451","title":"Bridging the Domain Gap for Multi-Agent Perception","created":"2022-10-16","cited_by_count":60},{"id":"1803.11316","title":"Task-Driven Super Resolution: Object Detection in Low-resolution Images","created":"2018-03-30","cited_by_count":53},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51},{"id":"2103.09950","title":"Learning to Resize Images for Computer Vision Tasks","created":"2021-03-17","cited_by_count":45},{"id":"1706.04284","title":"When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach","created":"2017-06-14","cited_by_count":42},{"id":"2004.03015","title":"Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment","created":"2020-04-06","cited_by_count":28},{"id":"1803.11366","title":"Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition","created":"2018-03-30","cited_by_count":27},{"id":"2105.01237","title":"COMISR: Compression-Informed Video Super-Resolution","created":"2021-05-04","cited_by_count":26},{"id":"2202.01653","title":"Learning strides in convolutional neural networks","created":"2022-02-03","cited_by_count":26},{"id":"2108.03489","title":"Impact of Aliasing on Generalization in Deep Convolutional Networks","created":"2021-08-07","cited_by_count":25},{"id":"1709.03919","title":"End-to-End United Video Dehazing and Detection","created":"2017-09-12","cited_by_count":24},{"id":"1710.07558","title":"Classification Driven Dynamic Image Enhancement","created":"2017-10-20","cited_by_count":15},{"id":"2002.00113","title":"Better Compression with Deep Pre-Editing","created":"2020-02-01","cited_by_count":9},{"id":"2204.12022","title":"Estimating the Resize Parameter in End-to-end Learned Image Compression","created":"2022-04-26","cited_by_count":5},{"id":"1606.07396","title":"Fast Multi-Layer Laplacian Enhancement","created":"2016-06-23","cited_by_count":3},{"id":"1904.05034","title":"ThumbNet: One Thumbnail Image Contains All You Need for Recognition","created":"2019-04-10","cited_by_count":2}],"next_cursor":null}