{"list":"other","total":67,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"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":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"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":"2310.01415","title":"GPT-Driver: Learning to Drive with GPT","created":"2023-10-02","cited_by_count":347},{"id":"2108.09640","title":"DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets","created":"2021-08-22","cited_by_count":295},{"id":"1809.10732","title":"Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks","created":"2018-09-18","cited_by_count":289},{"id":"2207.05844","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","created":"2022-07-12","cited_by_count":280},{"id":"2209.13508","title":"Motion Transformer with Global Intention Localization and Local Movement Refinement","created":"2022-09-27","cited_by_count":270},{"id":"2111.14973","title":"MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction","created":"2021-11-29","cited_by_count":246},{"id":"2101.06679","title":"End-to-end Interpretable Neural Motion Planner","created":"2021-01-17","cited_by_count":242},{"id":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239},{"id":"2012.12395","title":"Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net","created":"2020-12-22","cited_by_count":228},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"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":"1905.01296","title":"PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings","created":"2019-05-03","cited_by_count":179},{"id":"1911.00997","title":"Multiple Futures Prediction","created":"2019-11-04","cited_by_count":178},{"id":"1910.06528","title":"End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds","created":"2019-10-15","cited_by_count":171},{"id":"2305.06242","title":"Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving","created":"2023-05-10","cited_by_count":169},{"id":"2106.08417","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","created":"2021-06-15","cited_by_count":165},{"id":"2310.08710","title":"Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research","created":"2023-10-12","cited_by_count":160},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158},{"id":"2309.16534","title":"MotionLM: Multi-Agent Motion Forecasting as Language Modeling","created":"2023-09-28","cited_by_count":156},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"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":"2005.14711","title":"PnPNet: End-to-End Perception and Prediction with Tracking in the Loop","created":"2020-05-29","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":"2105.10968","title":"HOME: Heatmap Output for future Motion Estimation","created":"2021-05-23","cited_by_count":122},{"id":"1906.08945","title":"Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions","created":"2019-06-21","cited_by_count":117},{"id":"2208.01582","title":"ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries","created":"2022-08-02","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":"1910.08233","title":"Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data","created":"2019-10-18","cited_by_count":104},{"id":"2205.00613","title":"MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries","created":"2022-05-02","cited_by_count":91},{"id":"2202.11884","title":"M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction","created":"2022-02-24","cited_by_count":81},{"id":"2003.11476","title":"PiP: Planning-informed Trajectory Prediction for Autonomous Driving","created":"2020-03-25","cited_by_count":80},{"id":"2008.10587","title":"What-If Motion Prediction for Autonomous Driving","created":"2020-08-24","cited_by_count":80},{"id":"2006.03340","title":"MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction","created":"2020-06-05","cited_by_count":69},{"id":"2003.03212","title":"Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding","created":"2020-03-06","cited_by_count":68},{"id":"2104.09959","title":"Identifying Driver Interactions via Conditional Behavior Prediction","created":"2021-04-20","cited_by_count":48},{"id":"2008.11901","title":"Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving","created":"2020-08-27","cited_by_count":41},{"id":"2210.08064","title":"LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds","created":"2022-10-14","cited_by_count":41},{"id":"2212.08710","title":"JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Driving","created":"2022-12-16","cited_by_count":40},{"id":"2006.02000","title":"MultiXNet: Multiclass Multistage Multimodal Motion Prediction","created":"2020-06-03","cited_by_count":31},{"id":"2109.11094","title":"PredictionNet: Real-Time Joint Probabilistic Traffic Prediction for Planning, Control, and Simulation","created":"2021-09-23","cited_by_count":29},{"id":"2304.03834","title":"WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting","created":"2023-04-07","cited_by_count":28},{"id":"2010.12007","title":"PRANK: motion Prediction based on RANKing","created":"2020-10-22","cited_by_count":22},{"id":"2206.02163","title":"MotionCNN: A Strong Baseline for Motion Prediction in Autonomous Driving","created":"2022-06-05","cited_by_count":21},{"id":"2003.08744","title":"PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous driving","created":"2020-03-09","cited_by_count":19},{"id":"2101.06832","title":"Deep Structured Reactive Planning","created":"2021-01-18","cited_by_count":19},{"id":"2310.10357","title":"BEVGPT: Generative Pre-trained Large Model for Autonomous Driving Prediction, Decision-Making, and Planning","created":"2023-10-16","cited_by_count":15}],"next_cursor":null}