{"list":"other","total":93,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"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":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"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":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"2103.09213","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","created":"2021-03-16","cited_by_count":199},{"id":"1903.07504","title":"Understanding the Limitations of CNN-based Absolute Camera Pose Regression","created":"2019-03-18","cited_by_count":177},{"id":"2002.12324","title":"Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC","created":"2020-02-27","cited_by_count":176},{"id":"1709.08429","title":"DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks","created":"2017-09-25","cited_by_count":175},{"id":"1802.10171","title":"Tell Me Where to Look: Guided Attention Inference Network","created":"2018-02-27","cited_by_count":169},{"id":"1712.03342","title":"Geometry-Aware Learning of Maps for Camera Localization","created":"2017-12-09","cited_by_count":161},{"id":"1506.02158","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","created":"2015-06-06","cited_by_count":159},{"id":"1711.10228","title":"Learning Less is More - 6D Camera Localization via 3D Surface Regression","created":"2017-11-28","cited_by_count":146},{"id":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"id":"1611.07890","title":"Image-based localization using LSTMs for structured feature correlation","created":"2016-11-23","cited_by_count":136},{"id":"1509.05909","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","created":"2015-09-19","cited_by_count":134},{"id":"1911.08670","title":"MMTM: Multimodal Transfer Module for CNN Fusion","created":"2019-11-20","cited_by_count":129},{"id":"2012.01909","title":"Patch2Pix: Epipolar-Guided Pixel-Level Correspondences","created":"2020-12-03","cited_by_count":129},{"id":"1805.06334","title":"Auxiliary Tasks in Multi-task Learning","created":"2018-05-16","cited_by_count":108},{"id":"2103.11468","title":"Learning Multi-Scene Absolute Pose Regression with Transformers","created":"2021-03-21","cited_by_count":108},{"id":"1804.00168","title":"Learning to Navigate in Cities Without a Map","created":"2018-03-31","cited_by_count":104},{"id":"1804.06120","title":"The TUM VI Benchmark for Evaluating Visual-Inertial Odometry","created":"2018-04-17","cited_by_count":99},{"id":"1909.06216","title":"Hierarchical Scene Coordinate Classification and Regression for Visual Localization","created":"2019-09-13","cited_by_count":93},{"id":"1909.03557","title":"AtLoc: Attention Guided Camera Localization","created":"2019-09-08","cited_by_count":92},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"1707.09733","title":"Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network","created":"2017-07-31","cited_by_count":79},{"id":"1908.02484","title":"Expert Sample Consensus Applied to Camera Re-Localization","created":"2019-08-07","cited_by_count":70},{"id":"1703.07971","title":"Image-based Localization using Hourglass Networks","created":"2017-03-23","cited_by_count":63},{"id":"2109.00524","title":"On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation","created":"2021-09-01","cited_by_count":63},{"id":"1603.05772","title":"Learning to Navigate the Energy Landscape","created":"2016-03-18","cited_by_count":62},{"id":"1804.08366","title":"VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry","created":"2018-04-23","cited_by_count":61},{"id":"1908.01293","title":"To Learn or Not to Learn: Visual Localization from Essential Matrices","created":"2019-08-04","cited_by_count":61},{"id":"1803.03642","title":"Deep Auxiliary Learning for Visual Localization and Odometry","created":"2018-03-09","cited_by_count":59},{"id":"1702.06521","title":"VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization","created":"2017-02-21","cited_by_count":58},{"id":"1809.09767","title":"Night-to-Day Image Translation for Retrieval-based Localization","created":"2018-09-26","cited_by_count":57},{"id":"1909.09803","title":"Visual Odometry Revisited: What Should Be Learnt?","created":"2019-09-21","cited_by_count":57},{"id":"2102.11603","title":"SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition","created":"2021-02-23","cited_by_count":57},{"id":"1802.02209","title":"IONet: Learning to Cure the Curse of Drift in Inertial Odometry","created":"2018-01-30","cited_by_count":55},{"id":"1701.08376","title":"VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem","created":"2017-01-29","cited_by_count":51},{"id":"1901.03638","title":"A General Optimization-based Framework for Local Odometry Estimation with Multiple Sensors","created":"2019-01-11","cited_by_count":45},{"id":"2007.02693","title":"Auxiliary Learning by Implicit Differentiation","created":"2020-06-22","cited_by_count":45},{"id":"2003.10629","title":"KFNet: Learning Temporal Camera Relocalization using Kalman Filtering","created":"2020-03-24","cited_by_count":43},{"id":"1912.00623","title":"Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task","created":"2019-12-02","cited_by_count":39},{"id":"1804.05625","title":"Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization","created":"2018-04-16","cited_by_count":35},{"id":"1903.01534","title":"Selective Sensor Fusion for Neural Visual-Inertial Odometry","created":"2019-03-04","cited_by_count":34},{"id":"2103.10796","title":"CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization","created":"2021-03-19","cited_by_count":34},{"id":"1610.05949","title":"Visual-Inertial Monocular SLAM with Map Reuse","created":"2016-10-19","cited_by_count":32},{"id":"2010.06323","title":"LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization","created":"2020-10-13","cited_by_count":28},{"id":"1906.11435","title":"DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints","created":"2019-06-27","cited_by_count":27},{"id":"1910.14215","title":"Multivariate Uncertainty in Deep Learning","created":"2019-10-31","cited_by_count":27},{"id":"1505.00393","title":"ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks","created":"2015-05-03","cited_by_count":24},{"id":"1911.09968","title":"SelfVIO: Self-Supervised Deep Monocular Visual-Inertial Odometry and Depth Estimation","created":"2019-11-22","cited_by_count":24},{"id":"1711.10250","title":"maplab: An Open Framework for Research in Visual-inertial Mapping and Localization","created":"2017-11-28","cited_by_count":23},{"id":"2001.07252","title":"UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision","created":"2020-01-20","cited_by_count":17},{"id":"1811.04370","title":"Improved Visual Relocalization by Discovering Anchor Points","created":"2018-11-11","cited_by_count":16},{"id":"1705.04300","title":"Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias and Rolling Shutter Effect","created":"2017-05-11","cited_by_count":12},{"id":"1912.03426","title":"Self-Supervised 3D Keypoint Learning for Ego-motion Estimation","created":"2019-12-07","cited_by_count":12},{"id":"2008.13504","title":"Deep Probabilistic Feature-metric Tracking","created":"2020-08-31","cited_by_count":12},{"id":"1804.03789","title":"Geometric Consistency for Self-Supervised End-to-End Visual Odometry","created":"2018-04-11","cited_by_count":11},{"id":"1912.08263","title":"ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization","created":"2019-12-17","cited_by_count":11},{"id":"1710.07965","title":"Backtracking Regression Forests for Accurate Camera Relocalization","created":"2017-10-22","cited_by_count":10},{"id":"1809.06445","title":"Efficient 2D-3D Matching for Multi-Camera Visual Localization","created":"2018-09-17","cited_by_count":10},{"id":"1812.07869","title":"Deep Global-Relative Networks for End-to-End 6-DoF Visual Localization and Odometry","created":"2018-12-19","cited_by_count":10},{"id":"2012.12014","title":"Do We Really Need Scene-specific Pose Encoders?","created":"2020-12-22","cited_by_count":10},{"id":"1810.03414","title":"Dense Multimodal Fusion for Hierarchically Joint Representation","created":"2018-10-08","cited_by_count":8},{"id":"1607.03949","title":"Large Scale SfM with the Distributed Camera Model","created":"2016-07-13","cited_by_count":7},{"id":"1709.06019","title":"LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation","created":"2017-09-18","cited_by_count":7},{"id":"1702.02175","title":"Keyframe-Based Visual-Inertial Online SLAM with Relocalization","created":"2017-02-07","cited_by_count":6},{"id":"1803.01549","title":"Relocalization, Global Optimization and Map Merging for Monocular Visual-Inertial SLAM","created":"2018-03-05","cited_by_count":6},{"id":"1904.08105","title":"DistanceNet: Estimating Traveled Distance from Monocular Images using a Recurrent Convolutional Neural Network","created":"2019-04-17","cited_by_count":4},{"id":"1604.08087","title":"Consistent Map-based 3D Localization on Mobile Devices","created":"2016-04-27","cited_by_count":3},{"id":"1803.07838","title":"An Experimental Study on Relative and Absolute Pose Graph Fusion for Vehicle Localization","created":"2018-03-21","cited_by_count":3},{"id":"1810.05456","title":"Modeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial Odometry","created":"2018-10-12","cited_by_count":2},{"id":"1909.10312","title":"How to improve CNN-based 6-DoF camera pose estimation","created":"2019-09-23","cited_by_count":1},{"id":"1912.09260","title":"Deep Reinforcement Learning for Motion Planning of Mobile Robots","created":"2019-12-19","cited_by_count":1}],"next_cursor":null}