{"list":"other","total":113,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"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":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"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":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"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":"1910.12430","title":"Differentiable Convex Optimization Layers","created":"2019-10-28","cited_by_count":465},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"2104.09044","title":"Distilling Knowledge via Knowledge Review","created":"2021-04-19","cited_by_count":288},{"id":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"1907.12209","title":"Enforcing geometric constraints of virtual normal for depth prediction","created":"2019-07-29","cited_by_count":234},{"id":"1805.04409","title":"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing","created":"2018-05-11","cited_by_count":224},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"2003.01060","title":"D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry","created":"2020-03-02","cited_by_count":206},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2011.02910","title":"Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers","created":"2020-11-05","cited_by_count":190},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190},{"id":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2005.06209","title":"On the uncertainty of self-supervised monocular depth estimation","created":"2020-05-13","cited_by_count":182},{"id":"1806.04807","title":"BA-Net: Dense Bundle Adjustment Network","created":"2018-06-13","cited_by_count":175},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168},{"id":"2203.01502","title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","created":"2022-03-03","cited_by_count":153},{"id":"1704.04058","title":"Solving ill-posed inverse problems using iterative deep neural networks","created":"2017-04-13","cited_by_count":145},{"id":"1803.08673","title":"Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries","created":"2018-03-23","cited_by_count":145},{"id":"1807.00275","title":"Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera","created":"2018-07-01","cited_by_count":140},{"id":"1812.11941","title":"High Quality Monocular Depth Estimation via Transfer Learning","created":"2018-12-31","cited_by_count":133},{"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":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125},{"id":"1702.02706","title":"Semi-Supervised Deep Learning for Monocular Depth Map Prediction","created":"2017-02-09","cited_by_count":109},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107},{"id":"1411.6387","title":"Deep Convolutional Neural Fields for Depth Estimation from a Single Image","created":"2014-11-24","cited_by_count":106},{"id":"2203.15132","title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","created":"2022-03-28","cited_by_count":94},{"id":"2210.09071","title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention","created":"2022-10-17","cited_by_count":93},{"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":"2006.02535","title":"A Survey on Deep Learning Techniques for Stereo-based Depth Estimation","created":"2020-06-01","cited_by_count":90},{"id":"2004.02760","title":"Guiding Monocular Depth Estimation Using Depth-Attention Volume","created":"2020-04-06","cited_by_count":82},{"id":"1803.11029","title":"Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation","created":"2018-03-29","cited_by_count":78},{"id":"1604.03650","title":"Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks","created":"2016-04-13","cited_by_count":73},{"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":"1912.09697","title":"DeepSFM: Structure From Motion Via Deep Bundle Adjustment","created":"2019-12-20","cited_by_count":70},{"id":"2003.06620","title":"Monocular Depth Estimation Based On Deep Learning: An Overview","created":"2020-03-14","cited_by_count":68},{"id":"2012.02177","title":"DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion","created":"2020-12-03","cited_by_count":68},{"id":"2201.10830","title":"MonoDistill: Learning Spatial Features for Monocular 3D Object Detection","created":"2022-01-26","cited_by_count":68},{"id":"1808.06586","title":"Learning Monocular Depth by Distilling Cross-domain Stereo Networks","created":"2018-08-20","cited_by_count":64},{"id":"1810.01849","title":"SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation","created":"2018-10-03","cited_by_count":64},{"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":"2301.07668","title":"Behind the Scenes: Density Fields for Single View Reconstruction","created":"2023-01-18","cited_by_count":63},{"id":"1908.03706","title":"Exploiting temporal consistency for real-time video depth estimation","created":"2019-08-10","cited_by_count":61},{"id":"2001.00987","title":"DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling","created":"2019-12-24","cited_by_count":60},{"id":"2111.15669","title":"360MonoDepth: High-Resolution 360{\\deg} Monocular Depth Estimation","created":"2021-11-30","cited_by_count":60},{"id":"2011.11814","title":"MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera","created":"2020-11-24","cited_by_count":59},{"id":"2011.13118","title":"Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks","created":"2020-11-26","cited_by_count":59},{"id":"2004.05304","title":"Inter-Region Affinity Distillation for Road Marking Segmentation","created":"2020-04-11","cited_by_count":58},{"id":"2201.07436","title":"Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth","created":"2022-01-19","cited_by_count":58},{"id":"1904.07087","title":"Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth","created":"2019-04-15","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":"2009.00743","title":"Bidirectional Attention Network for Monocular Depth Estimation","created":"2020-09-01","cited_by_count":48},{"id":"1804.00413","title":"End-to-End Learning of Motion Representation for Video Understanding","created":"2018-04-02","cited_by_count":43},{"id":"1505.02206","title":"Learning image representations tied to ego-motion","created":"2015-05-08","cited_by_count":42},{"id":"2112.02306","title":"Toward Practical Monocular Indoor Depth Estimation","created":"2021-12-04","cited_by_count":42},{"id":"2103.16690","title":"Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion","created":"2021-03-30","cited_by_count":39},{"id":"1901.09402","title":"Monocular Depth Estimation: A Survey","created":"2019-01-27","cited_by_count":38},{"id":"1809.00646","title":"Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks","created":"2018-09-03","cited_by_count":31},{"id":"1809.02966","title":"LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo","created":"2018-09-09","cited_by_count":28},{"id":"1910.04858","title":"Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate","created":"2019-09-28","cited_by_count":28},{"id":"2110.08192","title":"Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation","created":"2021-10-15","cited_by_count":27}],"next_cursor":"100"}