{"list":"other","total":96,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"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":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"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":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"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":"2106.11810","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","created":"2021-06-22","cited_by_count":493},{"id":"2305.09617","title":"Towards Expert-Level Medical Question Answering with Large Language Models","created":"2023-05-16","cited_by_count":384},{"id":"2109.07644","title":"OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication","created":"2021-09-16","cited_by_count":304},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"2204.05575","title":"DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection","created":"2022-04-12","cited_by_count":273},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"2209.12836","title":"Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps","created":"2022-09-26","cited_by_count":255},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"2306.07962","title":"Parting with Misconceptions about Learning-based Vehicle Motion Planning","created":"2023-06-13","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":"1910.03088","title":"INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps","created":"2019-09-30","cited_by_count":231},{"id":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"1811.02790","title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","created":"2018-11-07","cited_by_count":204},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194},{"id":"2205.09743","title":"BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving","created":"2022-05-19","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":"2109.04456","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","created":"2021-09-09","cited_by_count":174},{"id":"1811.10200","title":"IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments","created":"2018-11-26","cited_by_count":163},{"id":"2202.08449","title":"V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving","created":"2022-02-17","cited_by_count":157},{"id":"1905.01489","title":"WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving","created":"2019-05-04","cited_by_count":144},{"id":"2308.00398","title":"DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving","created":"2023-08-01","cited_by_count":144},{"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":"2306.17770","title":"MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying","created":"2023-06-30","cited_by_count":140},{"id":"2311.01043","title":"LLM4Drive: A Survey of Large Language Models for Autonomous Driving","created":"2023-11-02","cited_by_count":136},{"id":"2002.09147","title":"SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances","created":"2020-02-21","cited_by_count":123},{"id":"1609.04653","title":"Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles","created":"2016-09-15","cited_by_count":117},{"id":"2205.09753","title":"HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding","created":"2022-04-30","cited_by_count":110},{"id":"1811.02307","title":"Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning","created":"2018-11-06","cited_by_count":102},{"id":"2305.10507","title":"ReasonNet: End-to-End Driving with Temporal and Global Reasoning","created":"2023-05-17","cited_by_count":93},{"id":"1711.01458","title":"DDD17: End-To-End DAVIS Driving Dataset","created":"2017-11-04","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":"2202.11884","title":"M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction","created":"2022-02-24","cited_by_count":81},{"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":"2007.12147","title":"CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending","created":"2020-07-23","cited_by_count":80},{"id":"2003.08284","title":"Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways","created":"2020-03-18","cited_by_count":77},{"id":"2003.10656","title":"Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection","created":"2020-03-24","cited_by_count":75},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","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":"2005.01456","title":"CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations","created":"2020-05-04","cited_by_count":60},{"id":"2003.13886","title":"TITAN: Future Forecast using Action Priors","created":"2020-03-31","cited_by_count":58},{"id":"1710.06288","title":"VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition","created":"2017-10-17","cited_by_count":56},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54},{"id":"2205.13817","title":"Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models","created":"2022-05-27","cited_by_count":53},{"id":"2009.06364","title":"4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving","created":"2020-09-14","cited_by_count":51},{"id":"2305.14715","title":"Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction","created":"2023-05-24","cited_by_count":48},{"id":"1611.08036","title":"Robotic Grasp Detection using Deep Convolutional Neural Networks","created":"2016-11-24","cited_by_count":47},{"id":"2205.00301","title":"ONCE-3DLanes: Building Monocular 3D Lane Detection","created":"2022-04-30","cited_by_count":44},{"id":"1411.7113","title":"Real time Detection of Lane Markers in Urban Streets","created":"2014-11-26","cited_by_count":41},{"id":"2008.05402","title":"DAWN: Vehicle Detection in Adverse Weather Nature Dataset","created":"2020-08-12","cited_by_count":41},{"id":"2211.16197","title":"FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs","created":"2022-11-27","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":"2305.04412","title":"Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors","created":"2023-05-08","cited_by_count":36},{"id":"2308.10280","title":"MacFormer: Map-Agent Coupled Transformer for Real-time and Robust Trajectory Prediction","created":"2023-08-20","cited_by_count":32},{"id":"2306.10508","title":"QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction","created":"2023-06-18","cited_by_count":31},{"id":"2105.02359","title":"MODS -- A USV-oriented object detection and obstacle segmentation benchmark","created":"2021-05-05","cited_by_count":27},{"id":"2304.11821","title":"Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Driving","created":"2023-04-24","cited_by_count":25},{"id":"2203.01437","title":"MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks","created":"2022-03-02","cited_by_count":24},{"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":"2108.08482","title":"VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection","created":"2021-08-19","cited_by_count":21},{"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":"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":"2301.12515","title":"LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection","created":"2023-01-29","cited_by_count":13},{"id":"2310.15670","title":"Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection","created":"2023-10-24","cited_by_count":13},{"id":"2107.13507","title":"The Reasonable Crowd: Towards evidence-based and interpretable models of driving behavior","created":"2021-07-28","cited_by_count":12},{"id":"2109.07648","title":"METEOR:A Dense, Heterogeneous, and Unstructured Traffic Dataset With Rare Behaviors","created":"2021-09-16","cited_by_count":12},{"id":"2303.10340","title":"3D Data Augmentation for Driving Scenes on Camera","created":"2023-03-18","cited_by_count":12},{"id":"2307.09788","title":"Density-invariant Features for Distant Point Cloud Registration","created":"2023-07-19","cited_by_count":12},{"id":"2304.04179","title":"Sparse Dense Fusion for 3D Object Detection","created":"2023-04-09","cited_by_count":9},{"id":"2303.02073","title":"How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement","created":"2023-03-03","cited_by_count":8},{"id":"2304.03105","title":"Geometric-aware Pretraining for Vision-centric 3D Object Detection","created":"2023-04-06","cited_by_count":8},{"id":"2206.08176","title":"Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot","created":"2022-06-16","cited_by_count":5},{"id":"2212.09368","title":"TAS-NIR: A VIS+NIR Dataset for Fine-grained Semantic Segmentation in Unstructured Outdoor Environments","created":"2022-12-19","cited_by_count":5},{"id":"2306.11429","title":"HDVIO: Improving Localization and Disturbance Estimation with Hybrid Dynamics VIO","created":"2023-06-20","cited_by_count":3},{"id":"2211.03407","title":"3D Harmonic Loss: Towards Task-consistent and Time-friendly 3D Object Detection on Edge for V2X Orchestration","created":"2022-11-07","cited_by_count":2},{"id":"1712.09356","title":"An Online Ride-Sharing Path Planning Strategy for Public Vehicle Systems","created":"2017-12-27","cited_by_count":1},{"id":"2212.10203","title":"ParallelNet: Multi-mode Trajectory Prediction by Multi-mode Trajectory Fusion","created":"2022-12-20","cited_by_count":1}],"next_cursor":null}