{"list":"other","total":113,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"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":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"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":"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":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"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":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"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":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"1511.02680","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","created":"2015-11-09","cited_by_count":218},{"id":"1904.04514","title":"High-Resolution Representations for Labeling Pixels and Regions","created":"2019-04-09","cited_by_count":211},{"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":"1905.02082","title":"ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals","created":"2019-05-06","cited_by_count":181},{"id":"1704.03489","title":"CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction","created":"2017-04-11","cited_by_count":152},{"id":"2001.00309","title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","created":"2020-01-02","cited_by_count":145},{"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":"1909.01300","title":"The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset","created":"2019-09-03","cited_by_count":134},{"id":"1806.00557","title":"CubeSLAM: Monocular 3D Object SLAM","created":"2018-06-01","cited_by_count":102},{"id":"2010.09076","title":"RADIATE: A Radar Dataset for Automotive Perception in Bad Weather","created":"2020-10-18","cited_by_count":100},{"id":"1808.08378","title":"Fusion++: Volumetric Object-Level SLAM","created":"2018-08-25","cited_by_count":98},{"id":"1804.09194","title":"MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects","created":"2018-04-24","cited_by_count":95},{"id":"1809.08379","title":"DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments","created":"2018-09-22","cited_by_count":91},{"id":"1804.04011","title":"QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM","created":"2018-04-10","cited_by_count":86},{"id":"1903.01568","title":"The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes","created":"2019-03-04","cited_by_count":80},{"id":"1812.07976","title":"MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM","created":"2018-12-19","cited_by_count":65},{"id":"1909.07541","title":"A*3D Dataset: Towards Autonomous Driving in Challenging Environments","created":"2019-09-17","cited_by_count":65},{"id":"2003.05691","title":"The Newer College Dataset: Handheld LiDAR, Inertial and Vision with Ground Truth","created":"2020-03-12","cited_by_count":61},{"id":"2004.04485","title":"NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstruction","created":"2020-04-09","cited_by_count":61},{"id":"1706.06629","title":"Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects","created":"2017-06-20","cited_by_count":47},{"id":"2010.07820","title":"DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM","created":"2020-10-15","cited_by_count":47},{"id":"2207.01404","title":"VECtor: A Versatile Event-Centric Benchmark for Multi-Sensor SLAM","created":"2022-07-04","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":"1709.09905","title":"X-View: Graph-Based Semantic Multi-View Localization","created":"2017-09-28","cited_by_count":43},{"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":"2108.07329","title":"TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset","created":"2021-08-16","cited_by_count":41},{"id":"2005.11052","title":"VDO-SLAM: A Visual Dynamic Object-aware SLAM System","created":"2020-05-22","cited_by_count":40},{"id":"2006.12567","title":"A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence","created":"2020-06-22","cited_by_count":35},{"id":"1607.02555","title":"A Photometrically Calibrated Benchmark For Monocular Visual Odometry","created":"2016-07-09","cited_by_count":32},{"id":"1609.07849","title":"Meaningful Maps With Object-Oriented Semantic Mapping","created":"2016-09-26","cited_by_count":31},{"id":"2004.08298","title":"IDDA: a large-scale multi-domain dataset for autonomous driving","created":"2020-04-17","cited_by_count":31},{"id":"2108.09481","title":"DSP-SLAM: Object Oriented SLAM with Deep Shape Priors","created":"2021-08-21","cited_by_count":30},{"id":"1703.08866","title":"Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras","created":"2017-03-26","cited_by_count":28},{"id":"1904.11781","title":"EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Association","created":"2019-04-26","cited_by_count":28},{"id":"1807.02062","title":"Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving","created":"2018-07-05","cited_by_count":26},{"id":"2002.08584","title":"Dynamic SLAM: The Need For Speed","created":"2020-02-20","cited_by_count":24},{"id":"2004.12730","title":"EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association","created":"2020-04-27","cited_by_count":24},{"id":"2007.01813","title":"AVP-SLAM: Semantic Visual Mapping and Localization for Autonomous Vehicles in the Parking Lot","created":"2020-07-03","cited_by_count":23},{"id":"1905.02781","title":"Robust Dense Mapping for Large-Scale Dynamic Environments","created":"2019-05-07","cited_by_count":21},{"id":"2103.05383","title":"Are We Ready for Unmanned Surface Vehicles in Inland Waterways? The USVInland Multisensor Dataset and Benchmark","created":"2021-03-09","cited_by_count":21},{"id":"2109.09903","title":"AirDOS: Dynamic SLAM benefits from Articulated Objects","created":"2021-09-21","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":"1909.06897","title":"Brno Urban Dataset -- The New Data for Self-Driving Agents and Mapping Tasks","created":"2019-09-15","cited_by_count":19},{"id":"2008.05058","title":"Dynamic Object Removal and Spatio-Temporal RGB-D Inpainting via Geometry-Aware Adversarial Learning","created":"2020-08-12","cited_by_count":19},{"id":"2109.04884","title":"SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints","created":"2021-09-10","cited_by_count":19},{"id":"2109.11316","title":"The Hilti SLAM Challenge Dataset","created":"2021-09-23","cited_by_count":18},{"id":"1809.09149","title":"Real-Time Monocular Object-Model Aware Sparse SLAM","created":"2018-09-24","cited_by_count":17},{"id":"1912.09513","title":"UrbanLoco: A Full Sensor Suite Dataset for Mapping and Localization in Urban Scenes","created":"2019-12-19","cited_by_count":17},{"id":"2003.12980","title":"ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings","created":"2020-03-29","cited_by_count":17},{"id":"2008.05416","title":"DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features","created":"2020-08-12","cited_by_count":17},{"id":"1909.11213","title":"Probabilistic Data Association via Mixture Models for Robust Semantic SLAM","created":"2019-09-24","cited_by_count":16},{"id":"1801.05269","title":"Long-term Visual Localization using Semantically Segmented Images","created":"2018-01-16","cited_by_count":15},{"id":"2102.05965","title":"VIODE: A Simulated Dataset to Address the Challenges of Visual-Inertial Odometry in Dynamic Environments","created":"2021-02-11","cited_by_count":15},{"id":"1607.00470","title":"Keyframe-based monocular SLAM: design, survey, and future directions","created":"2016-07-02","cited_by_count":13},{"id":"1909.03330","title":"EU Long-term Dataset with Multiple Sensors for Autonomous Driving","created":"2019-09-07","cited_by_count":13},{"id":"1912.05002","title":"TextSLAM: Visual SLAM with Planar Text Features","created":"2019-11-26","cited_by_count":11},{"id":"2012.02938","title":"Cirrus: A Long-range Bi-pattern LiDAR Dataset","created":"2020-12-05","cited_by_count":11},{"id":"2202.01938","title":"CFP-SLAM: A Real-time Visual SLAM Based on Coarse-to-Fine Probability in Dynamic Environments","created":"2022-02-04","cited_by_count":10},{"id":"2102.04036","title":"Simultaneous Localization and Mapping Related Datasets: A Comprehensive Survey","created":"2021-02-08","cited_by_count":9},{"id":"1907.09691","title":"Deep-SLAM++: Object-level RGBD SLAM based on class-specific deep shape priors","created":"2019-07-23","cited_by_count":8},{"id":"2008.00072","title":"Dynamic Object Tracking and Masking for Visual SLAM","created":"2020-07-31","cited_by_count":8},{"id":"1809.10239","title":"Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space","created":"2018-09-20","cited_by_count":6},{"id":"1910.14103","title":"CALC2.0: Combining Appearance, Semantic and Geometric Information for Robust and Efficient Visual Loop Closure","created":"2019-10-30","cited_by_count":6}],"next_cursor":"100"}