{"list":"other","total":92,"rows":[{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1711.02512","title":"Fine-tuning CNN Image Retrieval with No Human Annotation","created":"2017-11-03","cited_by_count":499},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286},{"id":"1804.00518","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","created":"2018-03-26","cited_by_count":208},{"id":"2402.14650","title":"GaussianPro: 3D Gaussian Splatting with Progressive Propagation","created":"2024-02-22","cited_by_count":200},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2308.00688","title":"AnyLoc: Towards Universal Visual Place Recognition","created":"2023-08-01","cited_by_count":163},{"id":"2303.02190","title":"MixVPR: Feature Mixing for Visual Place Recognition","created":"2023-03-03","cited_by_count":161},{"id":"2002.12186","title":"University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization","created":"2020-02-27","cited_by_count":157},{"id":"1707.05972","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","created":"2017-07-19","cited_by_count":156},{"id":"2003.02437","title":"Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning","created":"2020-03-05","cited_by_count":152},{"id":"2311.15937","title":"Optimal Transport Aggregation for Visual Place Recognition","created":"2023-11-27","cited_by_count":152},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143},{"id":"2011.12954","title":"RELLIS-3D Dataset: Data, Benchmarks and Analysis","created":"2020-11-17","cited_by_count":119},{"id":"2107.04286","title":"Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset","created":"2021-07-09","cited_by_count":118},{"id":"2011.04530","title":"MinkLoc3D: Point Cloud Based Large-Scale Place Recognition","created":"2020-11-09","cited_by_count":115},{"id":"2403.15530","title":"Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":113},{"id":"2206.08171","title":"K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions","created":"2022-06-16","cited_by_count":108},{"id":"2305.14059","title":"Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses","created":"2023-05-23","cited_by_count":107},{"id":"2210.10239","title":"GSV-Cities: Toward Appropriate Supervised Visual Place Recognition","created":"2022-10-19","cited_by_count":93},{"id":"1909.03557","title":"AtLoc: Attention Guided Camera Localization","created":"2019-09-08","cited_by_count":92},{"id":"1804.07437","title":"Vision Meets Drones: A Challenge","created":"2018-04-20","cited_by_count":81},{"id":"2204.10704","title":"SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite","created":"2022-04-22","cited_by_count":64},{"id":"1805.00881","title":"Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challenges","created":"2018-04-19","cited_by_count":54},{"id":"2203.09065","title":"STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset","created":"2022-03-17","cited_by_count":53},{"id":"2109.07982","title":"R3LIVE: A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package","created":"2021-09-10","cited_by_count":50},{"id":"2406.04340","title":"GLACE: Global Local Accelerated Coordinate Encoding","created":"2024-06-06","cited_by_count":48},{"id":"2203.00972","title":"Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training","created":"2022-03-02","cited_by_count":45},{"id":"2104.05327","title":"MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition","created":"2021-04-12","cited_by_count":41},{"id":"2305.13608","title":"VDD: Varied Drone Dataset for Semantic Segmentation","created":"2023-05-23","cited_by_count":40},{"id":"2302.14325","title":"BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images","created":"2023-02-28","cited_by_count":39},{"id":"2102.05346","title":"The Hessigheim 3D (H3D) Benchmark on Semantic Segmentation of High-Resolution 3D Point Clouds and Textured Meshes from UAV LiDAR and Multi-View-Stereo","created":"2021-02-10","cited_by_count":37},{"id":"2111.11739","title":"AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition","created":"2021-11-23","cited_by_count":36},{"id":"2202.00379","title":"NTU VIRAL: A Visual-Inertial-Ranging-Lidar Dataset, From an Aerial Vehicle Viewpoint","created":"2022-02-01","cited_by_count":29},{"id":"2112.09081","title":"CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data","created":"2021-12-16","cited_by_count":28},{"id":"2308.10491","title":"SynDrone -- Multi-modal UAV Dataset for Urban Scenarios","created":"2023-08-21","cited_by_count":28},{"id":"1906.08716","title":"Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehicles","created":"2019-06-20","cited_by_count":25},{"id":"2403.11247","title":"Compact 3D Gaussian Splatting For Dense Visual SLAM","created":"2024-03-17","cited_by_count":25},{"id":"2203.00893","title":"FAST-LIVO: Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry","created":"2022-03-02","cited_by_count":24},{"id":"2405.11936","title":"UAV-VisLoc: A Large-scale Dataset for UAV Visual Localization","created":"2024-05-20","cited_by_count":23},{"id":"2401.05971","title":"UAVD4L: A Large-Scale Dataset for UAV 6-DoF Localization","created":"2024-01-11","cited_by_count":22},{"id":"2404.04880","title":"GauU-Scene V2: Assessing the Reliability of Image-Based Metrics with Expansive Lidar Image Dataset Using 3DGS and NeRF","created":"2024-04-07","cited_by_count":21},{"id":"2105.07645","title":"Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimation","created":"2021-05-17","cited_by_count":19},{"id":"2211.11238","title":"RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments","created":"2022-11-21","cited_by_count":18},{"id":"2311.03198","title":"LCPR: A Multi-Scale Attention-Based LiDAR-Camera Fusion Network for Place Recognition","created":"2023-11-06","cited_by_count":17},{"id":"2312.15364","title":"WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments","created":"2023-12-23","cited_by_count":17},{"id":"2311.02872","title":"FocusTune: Tuning Visual Localization through Focus-Guided Sampling","created":"2023-11-06","cited_by_count":16},{"id":"2405.17705","title":"DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos","created":"2024-05-27","cited_by_count":16},{"id":"2401.14032","title":"GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting","created":"2024-01-25","cited_by_count":15},{"id":"2404.06050","title":"Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes","created":"2024-04-09","cited_by_count":15},{"id":"2409.19833","title":"HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes","created":"2024-09-30","cited_by_count":15},{"id":"2207.12317","title":"ALTO: A Large-Scale Dataset for UAV Visual Place Recognition and Localization","created":"2022-07-19","cited_by_count":12},{"id":"2309.08914","title":"Outram: One-shot Global Localization via Triangulated Scene Graph and Global Outlier Pruning","created":"2023-09-16","cited_by_count":9},{"id":"2409.07715","title":"FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments","created":"2024-09-12","cited_by_count":8},{"id":"2403.13395","title":"Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments","created":"2024-03-20","cited_by_count":7},{"id":"2410.22200","title":"EnvoDat: A Large-Scale Multisensory Dataset for Robotic Spatial Awareness and Semantic Reasoning in Heterogeneous Environments","created":"2024-10-29","cited_by_count":7},{"id":"2209.08258","title":"A real-time dynamic obstacle tracking and mapping system for UAV navigation and collision avoidance with an RGB-D camera","created":"2022-09-17","cited_by_count":5},{"id":"2310.08435","title":"MUN-FRL: A Visual Inertial LiDAR Dataset for Aerial Autonomous Navigation and Mapping","created":"2023-10-12","cited_by_count":5},{"id":"2010.12274","title":"VIRAL-Fusion: A Visual-Inertial-Ranging-Lidar Sensor Fusion Approach","created":"2020-10-23","cited_by_count":4},{"id":"2109.04686","title":"DIRECT: A Differential Dynamic Programming Based Framework for Trajectory Generation","created":"2021-09-10","cited_by_count":4},{"id":"2212.01536","title":"NEPTUNE: Nonentangling Trajectory Planning for Multiple Tethered Unmanned Vehicles","created":"2022-12-03","cited_by_count":4},{"id":"2403.01225","title":"A Cost-Effective Cooperative Exploration and Inspection Strategy for Heterogeneous Aerial System","created":"2024-03-02","cited_by_count":4},{"id":"2501.19274","title":"GO: The Great Outdoors Multimodal Dataset","created":"2025-01-31","cited_by_count":4},{"id":"2305.00271","title":"Path Planning for Multiple Tethered Robots Using Topological Braids","created":"2023-04-29","cited_by_count":2},{"id":"2503.07949","title":"QLIO: Quantized LiDAR-Inertial Odometry","created":"2025-03-11","cited_by_count":2},{"id":"2502.19242","title":"BEV-LIO(LC): BEV Image Assisted LiDAR-Inertial Odometry with Loop Closure","created":"2025-02-26","cited_by_count":1},{"id":"2503.06890","title":"AirSwarm: Enabling Cost-Effective Multi-UAV Research with COTS drones","created":"2025-03-10","cited_by_count":1}],"next_cursor":null}