{"list":"other","total":302,"rows":[{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"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":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"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":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"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":"1911.10150","title":"PointPainting: Sequential Fusion for 3D Object Detection","created":"2019-11-22","cited_by_count":449},{"id":"1911.08415","title":"GMAN: A Graph Multi-Attention Network for Traffic Prediction","created":"2019-11-11","cited_by_count":434},{"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":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","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":"2002.11927","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","created":"2020-02-27","cited_by_count":325},{"id":"2203.10638","title":"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer","created":"2022-03-20","cited_by_count":320},{"id":"1704.04394","title":"DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents","created":"2017-04-14","cited_by_count":310},{"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":"1806.01482","title":"SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints","created":"2018-06-05","cited_by_count":298},{"id":"2008.07519","title":"V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction","created":"2020-08-17","cited_by_count":292},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"1809.10732","title":"Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks","created":"2018-09-18","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":"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":"2001.01328","title":"Scalable Gradients for Stochastic Differential Equations","created":"2020-01-05","cited_by_count":271},{"id":"2209.13508","title":"Motion Transformer with Global Intention Localization and Local Movement Refinement","created":"2022-09-27","cited_by_count":270},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262},{"id":"1911.10298","title":"CoverNet: Multimodal Behavior Prediction using Trajectory Sets","created":"2019-11-23","cited_by_count":259},{"id":"2209.12836","title":"Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps","created":"2022-09-26","cited_by_count":255},{"id":"2111.14973","title":"MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction","created":"2021-11-29","cited_by_count":246},{"id":"2206.08920","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","created":"2022-06-17","cited_by_count":245},{"id":"2006.14480","title":"One Thousand and One Hours: Self-driving Motion Prediction Dataset","created":"2020-06-25","cited_by_count":240},{"id":"2004.02025","title":"It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction","created":"2020-04-04","cited_by_count":236},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"id":"1907.03395","title":"Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks","created":"2019-07-04","cited_by_count":229},{"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":"2005.08514","title":"Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction","created":"2020-05-18","cited_by_count":218},{"id":"2306.03083","title":"MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion","created":"2023-06-05","cited_by_count":213},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"2103.11624","title":"Multimodal Motion Prediction with Stacked Transformers","created":"2021-03-22","cited_by_count":208},{"id":"2111.00643","title":"Learning Distilled Collaboration Graph for Multi-Agent Perception","created":"2021-11-01","cited_by_count":194},{"id":"2210.17366","title":"Guided Conditional Diffusion for Controllable Traffic Simulation","created":"2022-10-31","cited_by_count":190},{"id":"1710.04689","title":"Social Attention: Modeling Attention in Human Crowds","created":"2017-10-12","cited_by_count":186},{"id":"2203.13777","title":"Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion","created":"2022-03-25","cited_by_count":185},{"id":"2003.08111","title":"Transformer Networks for Trajectory Forecasting","created":"2020-03-18","cited_by_count":181},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"1905.01296","title":"PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings","created":"2019-05-03","cited_by_count":179},{"id":"2003.13402","title":"Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks","created":"2020-03-30","cited_by_count":175},{"id":"2012.01526","title":"From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting","created":"2020-12-02","cited_by_count":167},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158},{"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":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2109.01827","title":"GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation","created":"2021-09-04","cited_by_count":146},{"id":"1909.10838","title":"Talk2Car: Taking Control of Your Self-Driving Car","created":"2019-09-24","cited_by_count":142},{"id":"2303.05760","title":"GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving","created":"2023-03-10","cited_by_count":141},{"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":"1903.08701","title":"LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving","created":"2019-03-20","cited_by_count":133},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132},{"id":"2303.10895","title":"Leapfrog Diffusion Model for Stochastic Trajectory Prediction","created":"2023-03-20","cited_by_count":132},{"id":"1904.04776","title":"Multi-Agent Tensor Fusion for Contextual Trajectory Prediction","created":"2019-04-09","cited_by_count":131},{"id":"2104.00563","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","created":"2021-02-19","cited_by_count":131},{"id":"2007.03639","title":"Human Trajectory Forecasting in Crowds: A Deep Learning Perspective","created":"2020-07-07","cited_by_count":129},{"id":"2211.07214","title":"Robust Collaborative 3D Object Detection in Presence of Pose Errors","created":"2022-11-14","cited_by_count":129},{"id":"2204.08770","title":"GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning","created":"2022-04-19","cited_by_count":128},{"id":"2003.09575","title":"Who2com: Collaborative Perception via Learnable Handshake Communication","created":"2020-03-21","cited_by_count":127},{"id":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126},{"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":"2007.12036","title":"Implicit Latent Variable Model for Scene-Consistent Motion Forecasting","created":"2020-07-23","cited_by_count":116},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114},{"id":"2106.15004","title":"Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals","created":"2021-06-28","cited_by_count":113},{"id":"1811.02146","title":"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents","created":"2018-11-06","cited_by_count":111},{"id":"1903.02793","title":"SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction","created":"2019-03-07","cited_by_count":111},{"id":"2106.10823","title":"3D Object Detection for Autonomous Driving: A Survey","created":"2021-06-21","cited_by_count":106},{"id":"2110.06607","title":"THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling","created":"2021-10-13","cited_by_count":101},{"id":"2104.01528","title":"SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction","created":"2021-04-04","cited_by_count":97},{"id":"2303.10876","title":"EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning","created":"2023-03-20","cited_by_count":97},{"id":"1906.03631","title":"Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction","created":"2019-06-09","cited_by_count":96},{"id":"2205.02222","title":"COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles","created":"2022-05-04","cited_by_count":95},{"id":"2103.03067","title":"TPCN: Temporal Point Cloud Networks for Motion Forecasting","created":"2021-03-04","cited_by_count":94},{"id":"1701.06699","title":"Imitating Driver Behavior with Generative Adversarial Networks","created":"2017-01-24","cited_by_count":93},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"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":"2310.02251","title":"Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving","created":"2023-10-03","cited_by_count":89},{"id":"2003.09405","title":"Explainable Object-induced Action Decision for Autonomous Vehicles","created":"2020-03-20","cited_by_count":88},{"id":"1910.03650","title":"Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting","created":"2019-10-08","cited_by_count":87},{"id":"2301.06262","title":"Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges","created":"2023-01-16","cited_by_count":87},{"id":"2203.11474","title":"Remember Intentions: Retrospective-Memory-based Trajectory Prediction","created":"2022-03-22","cited_by_count":86},{"id":"2207.08560","title":"Latency-Aware Collaborative Perception","created":"2022-07-18","cited_by_count":86},{"id":"1812.04767","title":"TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions","created":"2018-12-12","cited_by_count":82}],"next_cursor":"100"}