{"list":"other","total":117,"rows":[{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"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":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"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":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"1911.11236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","created":"2019-11-25","cited_by_count":585},{"id":"1901.02970","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","created":"2019-01-09","cited_by_count":495},{"id":"2103.12352","title":"iMAP: Implicit Mapping and Positioning in Real-Time","created":"2021-03-23","cited_by_count":476},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"2101.10994","title":"Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes","created":"2021-01-26","cited_by_count":426},{"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":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"1901.04780","title":"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion","created":"2019-01-15","cited_by_count":355},{"id":"1906.07165","title":"High Speed and High Dynamic Range Video with an Event Camera","created":"2019-06-15","cited_by_count":345},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"2010.13938","title":"Neural Unsigned Distance Fields for Implicit Function Learning","created":"2020-10-26","cited_by_count":265},{"id":"2012.10992","title":"Deep Continuous Fusion for Multi-Sensor 3D Object Detection","created":"2020-12-20","cited_by_count":263},{"id":"1710.07368","title":"SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud","created":"2017-10-19","cited_by_count":232},{"id":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"id":"1809.08495","title":"SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud","created":"2018-09-22","cited_by_count":228},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"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":"1904.08298","title":"Events-to-Video: Bringing Modern Computer Vision to Event Cameras","created":"2019-04-17","cited_by_count":193},{"id":"2007.00258","title":"LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping","created":"2020-07-01","cited_by_count":188},{"id":"1910.02490","title":"Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping","created":"2019-10-06","cited_by_count":184},{"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":"1807.02443","title":"Tangent Convolutions for Dense Prediction in 3D","created":"2018-07-06","cited_by_count":173},{"id":"1711.10871","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","created":"2017-11-29","cited_by_count":170},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163},{"id":"1901.01892","title":"Scale-Aware Trident Networks for Object Detection","created":"2019-01-07","cited_by_count":159},{"id":"1611.03631","title":"Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning","created":"2016-11-11","cited_by_count":150},{"id":"1709.06310","title":"Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios","created":"2017-09-19","cited_by_count":150},{"id":"2002.06289","title":"3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans","created":"2020-02-15","cited_by_count":144},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144},{"id":"1609.05130","title":"SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks","created":"2016-09-16","cited_by_count":135},{"id":"1806.05620","title":"DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes","created":"2018-06-14","cited_by_count":134},{"id":"1803.04523","title":"Event-based Moving Object Detection and Tracking","created":"2018-03-12","cited_by_count":127},{"id":"1902.04502","title":"Fast-SCNN: Fast Semantic Segmentation Network","created":"2019-02-12","cited_by_count":125},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104},{"id":"1903.12174","title":"TensorMask: A Foundation for Dense Object Segmentation","created":"2019-03-28","cited_by_count":101},{"id":"2105.11320","title":"SuMa++: Efficient LiDAR-based Semantic SLAM","created":"2021-05-24","cited_by_count":100},{"id":"1804.06120","title":"The TUM VI Benchmark for Evaluating Visual-Inertial Odometry","created":"2018-04-17","cited_by_count":99},{"id":"1903.01177","title":"PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things","created":"2019-03-04","cited_by_count":98},{"id":"1512.02363","title":"On-Manifold Preintegration for Real-Time Visual-Inertial Odometry","created":"2015-12-08","cited_by_count":95},{"id":"1709.06841","title":"UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning","created":"2017-09-20","cited_by_count":95},{"id":"1811.12039","title":"EV-SegNet: Semantic Segmentation for Event-based Cameras","created":"2018-11-29","cited_by_count":93},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"1909.10980","title":"PST900: RGB-Thermal Calibration, Dataset and Segmentation Network","created":"2019-09-20","cited_by_count":85},{"id":"1903.00268","title":"Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery","created":"2019-03-01","cited_by_count":80},{"id":"1805.11773","title":"Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice","created":"2018-05-30","cited_by_count":76},{"id":"1702.07389","title":"Continuous-Time Visual-Inertial Odometry for Event Cameras","created":"2017-02-23","cited_by_count":57},{"id":"1805.07931","title":"Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras","created":"2018-05-21","cited_by_count":57},{"id":"2106.14386","title":"Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems","created":"2021-06-28","cited_by_count":54},{"id":"2108.01176","title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","created":"2021-08-02","cited_by_count":52},{"id":"1808.01111","title":"LDSO: Direct Sparse Odometry with Loop Closure","created":"2018-08-03","cited_by_count":51},{"id":"1904.06504","title":"Visual-Inertial Mapping with Non-Linear Factor Recovery","created":"2019-04-13","cited_by_count":50},{"id":"2104.10831","title":"LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping","created":"2021-04-22","cited_by_count":45},{"id":"2107.00822","title":"F-LOAM: Fast LiDAR Odometry And Mapping","created":"2021-07-02","cited_by_count":45},{"id":"1901.03642","title":"A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors","created":"2019-01-11","cited_by_count":44},{"id":"2008.08974","title":"ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data","created":"2020-08-20","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":"2109.10165","title":"Panoptic Multi-TSDFs: a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistency","created":"2021-09-21","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":"2003.02425","title":"Who Make Drivers Stop? Towards Driver-centric Risk Assessment: Risk Object Identification via Causal Inference","created":"2020-03-05","cited_by_count":34},{"id":"1607.02555","title":"A Photometrically Calibrated Benchmark For Monocular Visual Odometry","created":"2016-07-09","cited_by_count":32},{"id":"1903.02144","title":"FIESTA: Fast Incremental Euclidean Distance Fields for Online Motion Planning of Aerial Robots","created":"2019-03-06","cited_by_count":31},{"id":"1810.00729","title":"SurfelMeshing: Online Surfel-Based Mesh Reconstruction","created":"2018-10-01","cited_by_count":29},{"id":"2004.01170","title":"DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes","created":"2020-04-02","cited_by_count":27},{"id":"1808.00692","title":"Online Temporal Calibration for Monocular Visual-Inertial Systems","created":"2018-08-02","cited_by_count":26},{"id":"2004.13154","title":"Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submaps","created":"2020-04-27","cited_by_count":26},{"id":"1904.06577","title":"Direct Sparse Mapping","created":"2019-04-13","cited_by_count":25},{"id":"1711.05805","title":"Robust and Precise Vehicle Localization based on Multi-sensor Fusion in Diverse City Scenes","created":"2017-11-15","cited_by_count":24},{"id":"2003.05593","title":"Learning to Segment 3D Point Clouds in 2D Image Space","created":"2020-03-12","cited_by_count":24},{"id":"2012.00514","title":"Multi-Modal Hybrid Architecture for Pedestrian Action Prediction","created":"2020-11-16","cited_by_count":23},{"id":"1807.07524","title":"LIMO: Lidar-Monocular Visual Odometry","created":"2018-07-19","cited_by_count":21},{"id":"1810.00818","title":"RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter","created":"2018-10-01","cited_by_count":21},{"id":"2107.08031","title":"Is attention to bounding boxes all you need for pedestrian action prediction?","created":"2021-07-16","cited_by_count":21},{"id":"1909.04250","title":"Real-time Scalable Dense Surfel Mapping","created":"2019-09-10","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":"1910.03858","title":"Intention Recognition of Pedestrians and Cyclists by 2D Pose Estimation","created":"2019-10-09","cited_by_count":19},{"id":"2103.13539","title":"Multi-View Fusion for Multi-Level Robotic Scene Understanding","created":"2021-03-25","cited_by_count":17}],"next_cursor":"100"}