{"list":"other","total":51,"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1802.05522","title":"Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints","created":"2018-02-15","cited_by_count":179},{"id":"1502.07411","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","created":"2015-02-26","cited_by_count":169},{"id":"1803.03893","title":"Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction","created":"2018-03-11","cited_by_count":159},{"id":"1811.06152","title":"Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos","created":"2018-11-15","cited_by_count":155},{"id":"1712.00175","title":"Learning Depth from Monocular Videos using Direct Methods","created":"2017-12-01","cited_by_count":154},{"id":"2007.06936","title":"Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance","created":"2020-07-14","cited_by_count":148},{"id":"1702.02706","title":"Semi-Supervised Deep Learning for Monocular Depth Map Prediction","created":"2017-02-09","cited_by_count":109},{"id":"1411.6387","title":"Deep Convolutional Neural Fields for Depth Estimation from a Single Image","created":"2014-11-24","cited_by_count":106},{"id":"1605.02305","title":"Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks","created":"2016-05-08","cited_by_count":91},{"id":"1803.11029","title":"Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation","created":"2018-03-29","cited_by_count":78},{"id":"1704.02157","title":"Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation","created":"2017-04-07","cited_by_count":70},{"id":"2001.00987","title":"DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling","created":"2019-12-24","cited_by_count":60},{"id":"1711.03665","title":"Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency","created":"2017-11-10","cited_by_count":40},{"id":"1604.07480","title":"Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks","created":"2016-04-25","cited_by_count":36},{"id":"2002.04479","title":"Depth Extraction from Video Using Non-parametric Sampling","created":"2019-12-24","cited_by_count":11},{"id":"2006.10853","title":"Image classification in frequency domain with 2SReLU: a second harmonics superposition activation function","created":"2020-06-18","cited_by_count":8},{"id":"2106.03505","title":"Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos","created":"2021-06-07","cited_by_count":7},{"id":"1503.08263","title":"CRF Learning with CNN Features for Image Segmentation","created":"2015-03-28","cited_by_count":6},{"id":"2006.15476","title":"Frequency learning for image classification","created":"2020-06-28","cited_by_count":5}],"next_cursor":null}