{"list":"other","total":52,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"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":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"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":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"1904.06587","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","created":"2019-04-13","cited_by_count":244},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190},{"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":"1904.04998","title":"Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras","created":"2019-04-10","cited_by_count":170},{"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":"2007.10603","title":"Feature-metric Loss for Self-supervised Learning of Depth and Egomotion","created":"2020-07-21","cited_by_count":140},{"id":"2002.12319","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","created":"2020-02-27","cited_by_count":134},{"id":"1907.05820","title":"Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera","created":"2019-07-12","cited_by_count":130},{"id":"1909.09051","title":"Self-Supervised Monocular Depth Hints","created":"2019-09-19","cited_by_count":127},{"id":"1807.11699","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","created":"2018-07-31","cited_by_count":88},{"id":"2010.16404","title":"Unsupervised Monocular Depth Learning in Dynamic Scenes","created":"2020-10-30","cited_by_count":84},{"id":"2004.00171","title":"The Edge of Depth: Explicit Constraints between Segmentation and Depth","created":"2020-04-01","cited_by_count":72},{"id":"1904.04144","title":"Learning monocular depth estimation infusing traditional stereo knowledge","created":"2019-04-08","cited_by_count":64},{"id":"2204.07616","title":"Multi-Frame Self-Supervised Depth with Transformers","created":"2022-04-15","cited_by_count":64},{"id":"2108.08829","title":"Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation","created":"2021-08-19","cited_by_count":55},{"id":"2008.03633","title":"Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes","created":"2020-08-09","cited_by_count":50},{"id":"1903.04202","title":"Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation","created":"2019-03-11","cited_by_count":49},{"id":"2109.12484","title":"Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation","created":"2021-09-26","cited_by_count":48},{"id":"2009.08250","title":"Parallax Attention for Unsupervised Stereo Correspondence Learning","created":"2020-09-16","cited_by_count":39},{"id":"2004.02138","title":"Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching","created":"2020-04-05","cited_by_count":36},{"id":"2207.11984","title":"RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation","created":"2022-07-25","cited_by_count":36},{"id":"2008.07130","title":"Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation","created":"2020-08-17","cited_by_count":34},{"id":"2103.07362","title":"PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss","created":"2021-03-12","cited_by_count":31},{"id":"2009.12840","title":"Adaptive confidence thresholding for monocular depth estimation","created":"2020-09-27","cited_by_count":25},{"id":"2209.07088","title":"Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation","created":"2022-09-15","cited_by_count":17},{"id":"2007.14511","title":"$S^3$Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data","created":"2020-07-28","cited_by_count":12},{"id":"2104.11288","title":"H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry","created":"2021-04-22","cited_by_count":12},{"id":"1611.07245","title":"Single-View and Multi-View Depth Fusion","created":"2016-11-22","cited_by_count":10},{"id":"1803.07512","title":"Fusion of stereo and still monocular depth estimates in a self-supervised learning context","created":"2018-03-20","cited_by_count":10},{"id":"2203.10925","title":"Learning Occlusion-Aware Coarse-to-Fine Depth Map for Self-supervised Monocular Depth Estimation","created":"2022-03-21","cited_by_count":6}],"next_cursor":null}