{"list":"other","total":133,"rows":[{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1904.08889","title":"KPConv: Flexible and Deformable Convolution for Point Clouds","created":"2019-04-18","cited_by_count":1205},{"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":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589},{"id":"1911.11236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","created":"2019-11-25","cited_by_count":585},{"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":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2106.11810","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","created":"2021-06-22","cited_by_count":493},{"id":"1911.10150","title":"PointPainting: Sequential Fusion for 3D Object Detection","created":"2019-11-22","cited_by_count":449},{"id":"2007.16100","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","created":"2020-07-31","cited_by_count":423},{"id":"1910.05449","title":"MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction","created":"2019-10-12","cited_by_count":420},{"id":"2007.13732","title":"Learning Lane Graph Representations for Motion Forecasting","created":"2020-07-27","cited_by_count":382},{"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":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315},{"id":"2208.14437","title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction","created":"2022-08-30","cited_by_count":314},{"id":"2211.10439","title":"BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision","created":"2022-11-18","cited_by_count":302},{"id":"1809.10732","title":"Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks","created":"2018-09-18","cited_by_count":289},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281},{"id":"2003.14032","title":"PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation","created":"2020-03-31","cited_by_count":275},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262},{"id":"2206.08920","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","created":"2022-06-17","cited_by_count":245},{"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":"2006.14480","title":"One Thousand and One Hours: Self-driving Motion Prediction Dataset","created":"2020-06-25","cited_by_count":240},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"1811.08188","title":"Orthographic Feature Transform for Monocular 3D Object Detection","created":"2018-11-20","cited_by_count":202},{"id":"2308.05736","title":"MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction","created":"2023-08-10","cited_by_count":193},{"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":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"2004.06320","title":"A2D2: Audi Autonomous Driving Dataset","created":"2020-04-14","cited_by_count":190},{"id":"2112.12610","title":"PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving","created":"2021-12-23","cited_by_count":190},{"id":"1712.06080","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","created":"2017-12-17","cited_by_count":187},{"id":"2003.13402","title":"Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks","created":"2020-03-30","cited_by_count":175},{"id":"1906.03560","title":"Cross-view Semantic Segmentation for Sensing Surroundings","created":"2019-06-09","cited_by_count":174},{"id":"2109.03805","title":"Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking","created":"2021-09-08","cited_by_count":166},{"id":"2211.10581","title":"Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion","created":"2022-11-19","cited_by_count":162},{"id":"2011.04841","title":"CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection","created":"2020-11-10","cited_by_count":161},{"id":"2109.01827","title":"GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation","created":"2021-09-04","cited_by_count":146},{"id":"2103.05073","title":"Offboard 3D Object Detection from Point Cloud Sequences","created":"2021-03-08","cited_by_count":145},{"id":"2308.12570","title":"StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction","created":"2023-08-24","cited_by_count":145},{"id":"1905.01489","title":"WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving","created":"2019-05-04","cited_by_count":144},{"id":"2504.04348","title":"OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning","created":"2025-04-06","cited_by_count":143},{"id":"1909.10838","title":"Talk2Car: Taking Control of Your Self-Driving Car","created":"2019-09-24","cited_by_count":142},{"id":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140},{"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":"2203.04050","title":"BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs","created":"2022-03-08","cited_by_count":123},{"id":"2312.03661","title":"Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving","created":"2023-12-06","cited_by_count":123},{"id":"2008.01550","title":"Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation","created":"2020-08-04","cited_by_count":112},{"id":"1811.02146","title":"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents","created":"2018-11-06","cited_by_count":111},{"id":"2309.04379","title":"Language Prompt for Autonomous Driving","created":"2023-09-08","cited_by_count":111},{"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":"2403.04133","title":"Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving","created":"2024-03-07","cited_by_count":104},{"id":"2110.06607","title":"THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling","created":"2021-10-13","cited_by_count":101},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"id":"2305.14018","title":"Sparse4D v2: Recurrent Temporal Fusion with Sparse Model","created":"2023-05-23","cited_by_count":93},{"id":"2001.10117","title":"Canadian Adverse Driving Conditions Dataset","created":"2020-01-27","cited_by_count":87},{"id":"2012.04934","title":"AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation","created":"2020-12-09","cited_by_count":87},{"id":"2308.16477","title":"PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction","created":"2023-08-31","cited_by_count":85},{"id":"1804.02176","title":"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks","created":"2018-04-06","cited_by_count":84},{"id":"2304.10440","title":"OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping","created":"2023-04-20","cited_by_count":83},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83},{"id":"2306.09700","title":"End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve","created":"2023-06-16","cited_by_count":82},{"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":"2012.11704","title":"HDNET: Exploiting HD Maps for 3D Object Detection","created":"2020-12-21","cited_by_count":78},{"id":"2302.13130","title":"Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting","created":"2023-02-25","cited_by_count":78},{"id":"2102.08009","title":"EfficientLPS: Efficient LiDAR Panoptic Segmentation","created":"2021-02-16","cited_by_count":76},{"id":"2203.10168","title":"Boreas: A Multi-Season Autonomous Driving Dataset","created":"2022-03-18","cited_by_count":76},{"id":"2003.10656","title":"Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection","created":"2020-03-24","cited_by_count":75},{"id":"2204.13483","title":"TJ4DRadSet: A 4D Radar Dataset for Autonomous Driving","created":"2022-04-28","cited_by_count":75},{"id":"2209.09385","title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception","created":"2022-09-19","cited_by_count":74},{"id":"2005.04078","title":"A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View","created":"2020-05-08","cited_by_count":72},{"id":"2303.08600","title":"MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving","created":"2023-03-15","cited_by_count":68},{"id":"2304.08481","title":"Neural Map Prior for Autonomous Driving","created":"2023-04-17","cited_by_count":68},{"id":"1909.07541","title":"A*3D Dataset: Towards Autonomous Driving in Challenging Environments","created":"2019-09-17","cited_by_count":65},{"id":"2104.00249","title":"LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agents","created":"2021-04-01","cited_by_count":64},{"id":"2110.11325","title":"Learning 3D Semantic Segmentation with only 2D Image Supervision","created":"2021-10-21","cited_by_count":60},{"id":"2205.07002","title":"Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap","created":"2022-05-14","cited_by_count":59},{"id":"2004.08745","title":"Learning to Evaluate Perception Models Using Planner-Centric Metrics","created":"2020-04-19","cited_by_count":49},{"id":"2208.01166","title":"Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions","created":"2022-08-01","cited_by_count":48},{"id":"2305.14715","title":"Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction","created":"2023-05-24","cited_by_count":48},{"id":"2205.00301","title":"ONCE-3DLanes: Building Monocular 3D Lane Detection","created":"2022-04-30","cited_by_count":44},{"id":"2312.06420","title":"Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It","created":"2023-12-11","cited_by_count":44},{"id":"2407.07462","title":"MAN TruckScenes: A multimodal dataset for autonomous trucking in diverse conditions","created":"2024-07-10","cited_by_count":41},{"id":"2301.04470","title":"InstaGraM: Instance-level Graph Modeling for Vectorized HD Map Learning","created":"2023-01-10","cited_by_count":40},{"id":"1803.10870","title":"Learning to Look around Objects for Top-View Representations of Outdoor Scenes","created":"2018-03-28","cited_by_count":37},{"id":"2504.03164","title":"NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving","created":"2025-04-04","cited_by_count":35}],"next_cursor":"100"}