{"list":"other","total":91,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2304.06706","title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields","created":"2023-04-13","cited_by_count":671},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"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":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2310.10642","title":"Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting","created":"2023-10-16","cited_by_count":476},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2207.07601","title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","created":"2022-07-15","cited_by_count":368},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2011.10379","title":"Neural Scene Graphs for Dynamic Scenes","created":"2020-11-20","cited_by_count":298},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2306.07962","title":"Parting with Misconceptions about Learning-based Vehicle Motion Planning","created":"2023-06-13","cited_by_count":242},{"id":"2312.03031","title":"Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?","created":"2023-12-05","cited_by_count":242},{"id":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222},{"id":"2401.01339","title":"Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting","created":"2024-01-02","cited_by_count":221},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2311.02077","title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","created":"2023-11-03","cited_by_count":217},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2305.10430","title":"Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes","created":"2023-05-17","cited_by_count":191},{"id":"2112.12610","title":"PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving","created":"2021-12-23","cited_by_count":190},{"id":"2307.15058","title":"MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving","created":"2023-07-27","cited_by_count":170},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"2005.08139","title":"Train in Germany, Test in The USA: Making 3D Object Detectors Generalize","created":"2020-05-17","cited_by_count":151},{"id":"2303.14536","title":"SUDS: Scalable Urban Dynamic Scenes","created":"2023-03-25","cited_by_count":151},{"id":"2102.12145","title":"GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator","created":"2021-02-24","cited_by_count":148},{"id":"2005.14711","title":"PnPNet: End-to-End Perception and Prediction with Tracking in the Loop","created":"2020-05-29","cited_by_count":144},{"id":"2311.18561","title":"Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering","created":"2023-11-30","cited_by_count":143},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132},{"id":"2208.01582","title":"ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries","created":"2022-08-02","cited_by_count":117},{"id":"2303.00749","title":"S-NeRF: Neural Radiance Fields for Street Views","created":"2023-03-01","cited_by_count":116},{"id":"2405.20323","title":"$\\textit{S}^3$Gaussian: Self-Supervised Street Gaussians for Autonomous Driving","created":"2024-05-30","cited_by_count":105},{"id":"2111.09621","title":"SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking","created":"2021-11-18","cited_by_count":103},{"id":"2406.18717","title":"Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos","created":"2024-06-26","cited_by_count":97},{"id":"2312.11458","title":"GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis","created":"2023-12-18","cited_by_count":95},{"id":"2203.07918","title":"GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting","created":"2022-03-15","cited_by_count":94},{"id":"2308.09882","title":"Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders","created":"2023-08-19","cited_by_count":73},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71},{"id":"2403.11324","title":"GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering","created":"2024-03-17","cited_by_count":52},{"id":"2407.02598","title":"AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstruction","created":"2024-07-02","cited_by_count":52},{"id":"2411.11921","title":"DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes","created":"2024-11-18","cited_by_count":45},{"id":"2208.00237","title":"RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation","created":"2022-07-30","cited_by_count":43},{"id":"2208.06661","title":"SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation","created":"2022-08-13","cited_by_count":41},{"id":"1901.07849","title":"AADS: Augmented Autonomous Driving Simulation using Data-driven Algorithms","created":"2019-01-23","cited_by_count":39},{"id":"2303.06880","title":"Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection","created":"2023-03-13","cited_by_count":39},{"id":"2406.03175","title":"Dynamic 3D Gaussian Fields for Urban Areas","created":"2024-06-05","cited_by_count":35},{"id":"2112.10203","title":"HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars","created":"2021-12-19","cited_by_count":33},{"id":"2207.08082","title":"CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement","created":"2022-07-17","cited_by_count":29},{"id":"1904.01975","title":"D$^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios","created":"2019-04-03","cited_by_count":28},{"id":"2212.04245","title":"Domain generalization of 3D semantic segmentation in autonomous driving","created":"2022-12-07","cited_by_count":25},{"id":"2308.06635","title":"3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking","created":"2023-08-12","cited_by_count":21},{"id":"2203.14387","title":"Towards Domain Generalization in Object Detection","created":"2022-03-27","cited_by_count":16},{"id":"2205.11853","title":"Real-Time Trajectory Planning for Autonomous Driving with Gaussian Process and Incremental Refinement","created":"2022-05-24","cited_by_count":14},{"id":"2308.01000","title":"MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalization","created":"2023-08-02","cited_by_count":14},{"id":"2405.00900","title":"LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes","created":"2024-05-01","cited_by_count":14},{"id":"2409.15727","title":"LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation","created":"2024-09-24","cited_by_count":14},{"id":"1801.10434","title":"Robust 3D Human Motion Reconstruction Via Dynamic Template Construction","created":"2018-01-31","cited_by_count":13},{"id":"2209.04796","title":"In Pursuit of Many: A Review of Modern Multiple Object Tracking Systems","created":"2022-09-11","cited_by_count":12},{"id":"2411.16106","title":"UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image","created":"2024-11-25","cited_by_count":12},{"id":"2402.17562","title":"An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains","created":"2024-02-27","cited_by_count":10},{"id":"2210.04127","title":"Towards Efficient Neural Scene Graphs by Learning Consistency Fields","created":"2022-10-09","cited_by_count":7},{"id":"2403.10099","title":"KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation","created":"2024-03-15","cited_by_count":6},{"id":"2404.03962","title":"RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications","created":"2024-04-05","cited_by_count":5},{"id":"2309.15411","title":"3D Multiple Object Tracking on Autonomous Driving: A Literature Review","created":"2023-09-27","cited_by_count":4},{"id":"2412.01552","title":"GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024","created":"2024-12-02","cited_by_count":3},{"id":"2408.16530","title":"A Comprehensive Review of 3D Object Detection in Autonomous Driving: Technological Advances and Future Directions","created":"2024-08-28","cited_by_count":2}],"next_cursor":null}