{"list":"other","total":60,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"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":"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":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"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":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352},{"id":"2203.17054","title":"BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection","created":"2022-03-31","cited_by_count":341},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"id":"1809.10732","title":"Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks","created":"2018-09-18","cited_by_count":289},{"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":"2111.14973","title":"MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction","created":"2021-11-29","cited_by_count":246},{"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":"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":"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":"2005.14711","title":"PnPNet: End-to-End Perception and Prediction with Tracking in the Loop","created":"2020-05-29","cited_by_count":144},{"id":"2208.01582","title":"ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries","created":"2022-08-02","cited_by_count":117},{"id":"2106.15004","title":"Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals","created":"2021-06-28","cited_by_count":113},{"id":"2210.06609","title":"TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios","created":"2022-10-12","cited_by_count":106},{"id":"2305.10507","title":"ReasonNet: End-to-End Driving with Temporal and Global Reasoning","created":"2023-05-17","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":"2211.17111","title":"BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deployment","created":"2022-11-30","cited_by_count":79},{"id":"2303.05970","title":"Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception","created":"2023-03-10","cited_by_count":65},{"id":"2306.12241","title":"ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling","created":"2023-06-21","cited_by_count":60},{"id":"2302.03802","title":"Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking","created":"2023-02-07","cited_by_count":54},{"id":"2303.12071","title":"ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals","created":"2023-03-21","cited_by_count":48},{"id":"2305.04412","title":"Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors","created":"2023-05-08","cited_by_count":36},{"id":"2403.11492","title":"SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction","created":"2024-03-18","cited_by_count":34},{"id":"2306.09281","title":"Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?","created":"2023-06-15","cited_by_count":22},{"id":"2202.05140","title":"Transferable and Adaptable Driving Behavior Prediction","created":"2022-02-10","cited_by_count":20},{"id":"2104.12446","title":"Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty","created":"2021-04-26","cited_by_count":19},{"id":"2010.14712","title":"Socially-Compatible Behavior Design of Autonomous Vehicles with Verification on Real Human Data","created":"2020-10-28","cited_by_count":18},{"id":"2406.04426","title":"DeTra: A Unified Model for Object Detection and Trajectory Forecasting","created":"2024-06-06","cited_by_count":15},{"id":"2110.09481","title":"MTP: Multi-Hypothesis Tracking and Prediction for Reduced Error Propagation","created":"2021-10-18","cited_by_count":14},{"id":"2305.17965","title":"Improving the Generalizability of Trajectory Prediction Models with Frenet-Based Domain Normalization","created":"2023-05-29","cited_by_count":13},{"id":"2306.03206","title":"MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences","created":"2023-06-05","cited_by_count":13},{"id":"2111.00788","title":"Hierarchical Adaptable and Transferable Networks (HATN) for Driving Behavior Prediction","created":"2021-11-01","cited_by_count":10},{"id":"2407.06683","title":"Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention","created":"2024-07-09","cited_by_count":8},{"id":"2306.08528","title":"Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images","created":"2023-06-14","cited_by_count":6},{"id":"2402.17892","title":"SWTrack: Multiple Hypothesis Sliding Window 3D Multi-Object Tracking","created":"2024-02-27","cited_by_count":5},{"id":"2407.04926","title":"JDT3D: Addressing the Gaps in LiDAR-Based Tracking-by-Attention","created":"2024-07-06","cited_by_count":4},{"id":"2306.10699","title":"Frame Fusion with Vehicle Motion Prediction for 3D Object Detection","created":"2023-06-19","cited_by_count":3}],"next_cursor":null}