{"list":"other","total":92,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"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":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"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":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"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":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"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":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"id":"2103.12352","title":"iMAP: Implicit Mapping and Positioning in Real-Time","created":"2021-03-23","cited_by_count":476},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"1606.05830","title":"Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age","created":"2016-06-19","cited_by_count":411},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"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":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2210.13641","title":"NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields","created":"2022-10-24","cited_by_count":188},{"id":"1905.04943","title":"Universal Invariant and Equivariant Graph Neural Networks","created":"2019-05-13","cited_by_count":183},{"id":"1905.02082","title":"ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals","created":"2019-05-06","cited_by_count":181},{"id":"1903.07504","title":"Understanding the Limitations of CNN-based Absolute Camera Pose Regression","created":"2019-03-18","cited_by_count":177},{"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":"1704.03489","title":"CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction","created":"2017-04-11","cited_by_count":152},{"id":"2105.00696","title":"Graph Learning: A Survey","created":"2021-05-03","cited_by_count":141},{"id":"1806.05620","title":"DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes","created":"2018-06-14","cited_by_count":134},{"id":"2001.05049","title":"DeepFactors: Real-Time Probabilistic Dense Monocular SLAM","created":"2020-01-14","cited_by_count":117},{"id":"2011.00359","title":"TartanVO: A Generalizable Learning-based VO","created":"2020-10-31","cited_by_count":108},{"id":"1806.00557","title":"CubeSLAM: Monocular 3D Object SLAM","created":"2018-06-01","cited_by_count":102},{"id":"2012.10885","title":"LieTransformer: Equivariant self-attention for Lie Groups","created":"2020-12-20","cited_by_count":100},{"id":"1709.06841","title":"UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning","created":"2017-09-20","cited_by_count":95},{"id":"1909.08605","title":"Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection","created":"2019-09-18","cited_by_count":94},{"id":"1909.03557","title":"AtLoc: Attention Guided Camera Localization","created":"2019-09-08","cited_by_count":92},{"id":"1809.08379","title":"DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments","created":"2018-09-22","cited_by_count":91},{"id":"1808.01900","title":"DeepTAM: Deep Tracking and Mapping","created":"2018-08-06","cited_by_count":87},{"id":"2004.01314","title":"Towards Better Generalization: Joint Depth-Pose Learning without PoseNet","created":"2020-04-03","cited_by_count":85},{"id":"1612.07386","title":"SE-Sync: A Certifiably Correct Algorithm for Synchronization over the Special Euclidean Group","created":"2016-12-21","cited_by_count":80},{"id":"1909.09803","title":"Visual Odometry Revisited: What Should Be Learnt?","created":"2019-09-21","cited_by_count":57},{"id":"1804.11188","title":"Can recurrent neural networks warp time?","created":"2018-03-23","cited_by_count":55},{"id":"1808.01111","title":"LDSO: Direct Sparse Odometry with Loop Closure","created":"2018-08-03","cited_by_count":51},{"id":"1911.05603","title":"Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM","created":"2019-11-13","cited_by_count":42},{"id":"2005.11052","title":"VDO-SLAM: A Visual Dynamic Object-aware SLAM System","created":"2020-05-22","cited_by_count":40},{"id":"2104.02538","title":"Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision","created":"2021-04-06","cited_by_count":37},{"id":"2105.07593","title":"Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation","created":"2021-05-17","cited_by_count":34},{"id":"1708.02813","title":"BlitzNet: A Real-Time Deep Network for Scene Understanding","created":"2017-08-09","cited_by_count":29},{"id":"2204.12831","title":"The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection","created":"2022-04-27","cited_by_count":29},{"id":"1712.00036","title":"Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight","created":"2017-11-30","cited_by_count":27},{"id":"1910.10672","title":"gradSLAM: Automagically differentiable SLAM","created":"2019-10-23","cited_by_count":27},{"id":"1907.04011","title":"UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor","created":"2019-07-09","cited_by_count":22},{"id":"1808.00288","title":"Attention-based Pyramid Aggregation Network for Visual Place Recognition","created":"2018-08-01","cited_by_count":21},{"id":"1802.05909","title":"iBoW-LCD: An Appearance-based Loop Closure Detection Approach using Incremental Bags of Binary Words","created":"2018-02-16","cited_by_count":20},{"id":"2104.00099","title":"LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method","created":"2021-03-31","cited_by_count":20},{"id":"1910.14532","title":"AQUALOC: An Underwater Dataset for Visual-Inertial-Pressure Localization","created":"2019-10-31","cited_by_count":18},{"id":"2008.05416","title":"DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features","created":"2020-08-12","cited_by_count":17},{"id":"2204.02163","title":"Leveraging Equivariant Features for Absolute Pose Regression","created":"2022-04-05","cited_by_count":17},{"id":"1607.00470","title":"Keyframe-based monocular SLAM: design, survey, and future directions","created":"2016-07-02","cited_by_count":13},{"id":"1902.03729","title":"UcoSLAM: Simultaneous Localization and Mapping by Fusion of KeyPoints and Squared Planar Markers","created":"2019-02-11","cited_by_count":12},{"id":"2009.02672","title":"Approaches, Challenges, and Applications for Deep Visual Odometry: Toward to Complicated and Emerging Areas","created":"2020-09-06","cited_by_count":11},{"id":"1811.09935","title":"Guided Feature Selection for Deep Visual Odometry","created":"2018-11-25","cited_by_count":10},{"id":"2104.06800","title":"VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good Enough","created":"2021-04-14","cited_by_count":9},{"id":"1902.03747","title":"Visual SLAM: Why Bundle Adjust?","created":"2019-02-11","cited_by_count":8},{"id":"1904.10324","title":"VITAMIN-E: VIsual Tracking And MappINg with Extremely Dense Feature Points","created":"2019-04-23","cited_by_count":8},{"id":"2102.04060","title":"OV$^{2}$SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications","created":"2021-02-08","cited_by_count":8},{"id":"1709.06019","title":"LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation","created":"2017-09-18","cited_by_count":7},{"id":"1802.09292","title":"Constructing Category-Specific Models for Monocular Object-SLAM","created":"2018-02-26","cited_by_count":7},{"id":"2207.00292","title":"Offset equivariant networks and their applications","created":"2022-07-01","cited_by_count":6},{"id":"2401.05396","title":"Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry","created":"2023-12-19","cited_by_count":6},{"id":"2108.08957","title":"Unified Representation of Geometric Primitives for Graph-SLAM Optimization Using Decomposed Quadrics","created":"2021-08-20","cited_by_count":5},{"id":"1903.08636","title":"An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM","created":"2019-03-20","cited_by_count":4},{"id":"2202.13221","title":"RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization","created":"2022-02-26","cited_by_count":4},{"id":"2201.13065","title":"Rigidity Preserving Image Transformations and Equivariance in Perspective","created":"2022-01-31","cited_by_count":3},{"id":"1706.03648","title":"Accurate Monocular Visual-inertial SLAM using a Map-assisted EKF Approach","created":"2017-06-12","cited_by_count":2},{"id":"2105.14065","title":"TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation","created":"2021-05-28","cited_by_count":2},{"id":"1704.01426","title":"The UMCD Dataset","created":"2017-04-05","cited_by_count":1},{"id":"2211.08480","title":"LiePoseNet: Heterogeneous Loss Function Based on Lie Group for Significant Speed-up of PoseNet Training Process","created":"2022-11-15","cited_by_count":1}],"next_cursor":null}