{"list":"other","total":55,"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":"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"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":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1811.00995","title":"Invertible Residual Networks","created":"2018-11-02","cited_by_count":365},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"1902.00275","title":"Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design","created":"2019-02-01","cited_by_count":262},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"1707.04585","title":"The Reversible Residual Network: Backpropagation Without Storing Activations","created":"2017-07-14","cited_by_count":217},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"1904.05049","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","created":"2019-04-10","cited_by_count":140},{"id":"2104.12533","title":"Visformer: The Vision-friendly Transformer","created":"2021-04-26","cited_by_count":137},{"id":"2007.00072","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","created":"2020-06-30","cited_by_count":108},{"id":"1709.03698","title":"Reversible Architectures for Arbitrarily Deep Residual Neural Networks","created":"2017-09-12","cited_by_count":70},{"id":"2104.10546","title":"Invertible Denoising Network: A Light Solution for Real Noise Removal","created":"2021-04-21","cited_by_count":68},{"id":"2102.07870","title":"Momentum Residual Neural Networks","created":"2021-02-15","cited_by_count":37},{"id":"1907.07945","title":"MintNet: Building Invertible Neural Networks with Masked Convolutions","created":"2019-07-18","cited_by_count":35},{"id":"2109.06381","title":"WINNet: Wavelet-inspired Invertible Network for Image Denoising","created":"2021-09-14","cited_by_count":34},{"id":"1810.10999","title":"Reversible Recurrent Neural Networks","created":"2018-10-25","cited_by_count":23},{"id":"1902.02729","title":"Reversible GANs for Memory-efficient Image-to-Image Translation","created":"2019-02-07","cited_by_count":19},{"id":"1911.10914","title":"Invert to Learn to Invert","created":"2019-11-25","cited_by_count":18},{"id":"1906.06148","title":"A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation","created":"2019-06-14","cited_by_count":16},{"id":"1911.11313","title":"Summarizing CPU and GPU Design Trends with Product Data","created":"2019-11-26","cited_by_count":10},{"id":"2105.03458","title":"Duplex Sequence-to-Sequence Learning for Reversible Machine Translation","created":"2021-05-07","cited_by_count":9},{"id":"2005.05220","title":"iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling","created":"2020-05-11","cited_by_count":7},{"id":"2104.09648","title":"Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation","created":"2021-04-19","cited_by_count":3},{"id":"2108.05862","title":"m-RevNet: Deep Reversible Neural Networks with Momentum","created":"2021-08-12","cited_by_count":3},{"id":"2003.07474","title":"Fully reversible neural networks for large-scale surface and sub-surface characterization via remote sensing","created":"2020-03-16","cited_by_count":2},{"id":"2103.09042","title":"Invertible Residual Network with Regularization for Effective Medical Image Segmentation","created":"2021-03-16","cited_by_count":2}],"next_cursor":null}