{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"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":"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":"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":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"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":"2008.08294","title":"TNT: Target-driveN Trajectory Prediction","created":"2020-08-19","cited_by_count":347},{"id":"2103.14023","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","created":"2021-03-25","cited_by_count":331},{"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":"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":"2402.13243","title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","created":"2024-02-20","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":"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":"1911.10298","title":"CoverNet: Multimodal Behavior Prediction using Trajectory Sets","created":"2019-11-23","cited_by_count":259},{"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":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"id":"2402.11502","title":"GenAD: Generative End-to-End Autonomous Driving","created":"2024-02-18","cited_by_count":225},{"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":"2003.08386","title":"DLow: Diversifying Latent Flows for Diverse Human Motion Prediction","created":"2020-03-18","cited_by_count":185},{"id":"2106.08417","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","created":"2021-06-15","cited_by_count":165},{"id":"2010.12035","title":"Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection","created":"2020-10-22","cited_by_count":138},{"id":"2104.00563","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","created":"2021-02-19","cited_by_count":131},{"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":"1910.08233","title":"Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data","created":"2019-10-18","cited_by_count":104},{"id":"2103.03067","title":"TPCN: Temporal Point Cloud Networks for Motion Forecasting","created":"2021-03-04","cited_by_count":94},{"id":"1808.05819","title":"Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving","created":"2018-08-17","cited_by_count":90},{"id":"2403.16440","title":"RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection","created":"2024-03-25","cited_by_count":82},{"id":"2006.03340","title":"MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction","created":"2020-06-05","cited_by_count":69},{"id":"2308.01006","title":"FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving","created":"2023-08-02","cited_by_count":67},{"id":"2403.15098","title":"UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction","created":"2024-03-22","cited_by_count":52},{"id":"2203.13641","title":"StretchBEV: Stretching Future Instance Prediction Spatially and Temporally","created":"2022-03-25","cited_by_count":47},{"id":"2206.04042","title":"Learning Ego 3D Representation as Ray Tracing","created":"2022-06-08","cited_by_count":43},{"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":"2311.08100","title":"PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving","created":"2023-11-14","cited_by_count":33},{"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":"2303.09998","title":"TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving","created":"2023-03-17","cited_by_count":30},{"id":"2209.07857","title":"GATraj: A Graph- and Attention-based Multi-Agent Trajectory Prediction Model","created":"2022-09-16","cited_by_count":26},{"id":"2407.13517","title":"Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Masks","created":"2024-07-18","cited_by_count":26},{"id":"2211.08609","title":"R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement","created":"2022-11-16","cited_by_count":24},{"id":"2010.12007","title":"PRANK: motion Prediction based on RANKing","created":"2020-10-22","cited_by_count":22},{"id":"2202.04488","title":"CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention","created":"2022-02-09","cited_by_count":21},{"id":"2004.12032","title":"StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification","created":"2020-04-25","cited_by_count":14},{"id":"2409.04979","title":"RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Network","created":"2024-09-08","cited_by_count":11},{"id":"2302.10463","title":"Vision-based Multi-future Trajectory Prediction: A Survey","created":"2023-02-21","cited_by_count":8},{"id":"2309.03750","title":"PBP: Path-based Trajectory Prediction for Autonomous Driving","created":"2023-09-07","cited_by_count":6},{"id":"2507.12083","title":"Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics","created":"2025-07-16","cited_by_count":6},{"id":"2104.11589","title":"SBNet: Segmentation-based Network for Natural Language-based Vehicle Search","created":"2021-04-22","cited_by_count":3}],"next_cursor":null}