{"list":"other","total":95,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"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":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"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":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"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":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"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":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"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":"2106.11810","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","created":"2021-06-22","cited_by_count":493},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"1910.05449","title":"MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction","created":"2019-10-12","cited_by_count":420},{"id":"1812.03079","title":"ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst","created":"2018-12-07","cited_by_count":397},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"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":"2008.08294","title":"TNT: Target-driveN Trajectory Prediction","created":"2020-08-19","cited_by_count":347},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2103.14023","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","created":"2021-03-25","cited_by_count":331},{"id":"2207.05844","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","created":"2022-07-12","cited_by_count":280},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"2209.13508","title":"Motion Transformer with Global Intention Localization and Local Movement Refinement","created":"2022-09-27","cited_by_count":270},{"id":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249},{"id":"2206.08129","title":"Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline","created":"2022-06-16","cited_by_count":248},{"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":"2207.14024","title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","created":"2022-07-28","cited_by_count":212},{"id":"2103.11624","title":"Multimodal Motion Prediction with Stacked Transformers","created":"2021-03-22","cited_by_count":208},{"id":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202},{"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":"1905.01296","title":"PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings","created":"2019-05-03","cited_by_count":179},{"id":"2210.02443","title":"Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection","created":"2022-10-05","cited_by_count":178},{"id":"1906.03560","title":"Cross-view Semantic Segmentation for Sensing Surroundings","created":"2019-06-09","cited_by_count":174},{"id":"2109.04456","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","created":"2021-09-09","cited_by_count":174},{"id":"1904.09730","title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","created":"2019-04-22","cited_by_count":163},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"1911.10868","title":"End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances","created":"2019-11-25","cited_by_count":149},{"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":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"2203.11934","title":"Learning from All Vehicles","created":"2022-03-22","cited_by_count":135},{"id":"2208.01582","title":"ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries","created":"2022-08-02","cited_by_count":117},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114},{"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":"2109.03814","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","created":"2021-09-08","cited_by_count":109},{"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":"2003.06754","title":"MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps","created":"2020-03-15","cited_by_count":100},{"id":"1807.03776","title":"CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving","created":"2018-07-10","cited_by_count":97},{"id":"2101.06547","title":"LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving","created":"2021-01-16","cited_by_count":96},{"id":"2205.00613","title":"MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries","created":"2022-05-02","cited_by_count":91},{"id":"2210.01917","title":"Differentiable Raycasting for Self-supervised Occupancy Forecasting","created":"2022-10-04","cited_by_count":84},{"id":"2103.07351","title":"Monocular Quasi-Dense 3D Object Tracking","created":"2021-03-12","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":"2207.10422","title":"Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving","created":"2022-07-21","cited_by_count":73},{"id":"2008.06041","title":"DSDNet: Deep Structured self-Driving Network","created":"2020-08-13","cited_by_count":62},{"id":"2111.08575","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","created":"2021-11-16","cited_by_count":60},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58},{"id":"2006.09917","title":"FISHING Net: Future Inference of Semantic Heatmaps In Grids","created":"2020-06-17","cited_by_count":55},{"id":"2008.05927","title":"End-to-end Contextual Perception and Prediction with Interaction Transformer","created":"2020-08-13","cited_by_count":54},{"id":"2203.13641","title":"StretchBEV: Stretching Future Instance Prediction Spatially and Temporally","created":"2022-03-25","cited_by_count":47},{"id":"2111.13672","title":"Immortal Tracker: Tracklet Never Dies","created":"2021-11-26","cited_by_count":42},{"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":"2006.02000","title":"MultiXNet: Multiclass Multistage Multimodal Motion Prediction","created":"2020-06-03","cited_by_count":31},{"id":"2009.07517","title":"MATS: An Interpretable Trajectory Forecasting Representation for Planning and Control","created":"2020-09-16","cited_by_count":30},{"id":"2209.08953","title":"Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving","created":"2022-09-19","cited_by_count":30},{"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":"2203.16297","title":"Forecasting from LiDAR via Future Object Detection","created":"2022-03-30","cited_by_count":28},{"id":"2011.01153","title":"Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving","created":"2020-11-02","cited_by_count":24},{"id":"2106.05966","title":"Learning by Watching","created":"2021-06-10","cited_by_count":22},{"id":"2003.08744","title":"PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous driving","created":"2020-03-09","cited_by_count":19},{"id":"2011.02403","title":"IDE-Net: Interactive Driving Event and Pattern Extraction from Human Data","created":"2020-11-04","cited_by_count":19},{"id":"2101.06832","title":"Deep Structured Reactive Planning","created":"2021-01-18","cited_by_count":19},{"id":"2208.10976","title":"Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking","created":"2022-08-23","cited_by_count":17},{"id":"2206.00991","title":"StopNet: Scalable Trajectory and Occupancy Prediction for Urban Autonomous Driving","created":"2022-06-02","cited_by_count":14}],"next_cursor":null}