{"url":"/dataset/argoverse","name":"Argoverse","full_name":null,"description_markdown":"**Argoverse** is a tracking benchmark with over 30K scenarios collected in Pittsburgh and Miami. Each scenario is a sequence of frames sampled at 10 HZ. Each sequence has an interesting object called “agent”, and the task is to predict the future locations of agents in a 3 seconds future horizon. The sequences are split into training, validation and test sets, which have 205,942, 39,472 and 78,143 sequences respectively. These splits have no geographical overlap.\r\n\r\nSource: [Learning Lane Graph Representations for Motion Forecasting](https://arxiv.org/abs/2007.13732)\r\nImage Source: [https://arxiv.org/pdf/1911.02620.pdf](https://arxiv.org/pdf/1911.02620.pdf)","description_withheld":null,"homepage":"https://www.argoverse.org/data.html","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/argoverse-3d-tracking-and-forecasting-with-1","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","first_author":"Ming-Fang Chang","url":null},"license":{"name":"Custom","url":"https://www.argoverse.org/about.html#terms-of-use"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Point cloud","url":"/datasets/modality/point-cloud"},{"name":"LiDAR","url":"/datasets/modality/lidar"}],"tasks":[{"name":"3D Object Detection","url":"/task/3d-object-detection","datasets_with_task":"/datasets/task/3d-object-detection"},{"name":"Trajectory Prediction","url":"/task/trajectory-prediction","datasets_with_task":"/datasets/task/trajectory-prediction"},{"name":"Motion Forecasting","url":"/task/motion-forecasting","datasets_with_task":"/datasets/task/motion-forecasting"},{"name":"Monocular Cross-View Road Scene Parsing(Road)","url":"/task/monocular-cross-view-road-scene-parsing-road","datasets_with_task":"/datasets/task/monocular-cross-view-road-scene-parsing-road"},{"name":"3D Object Tracking","url":"/task/3d-object-tracking","datasets_with_task":"/datasets/task/3d-object-tracking"},{"name":"Monocular Cross-View Road Scene Parsing(Vehicle)","url":"/task/monocular-cross-view-road-scene-parsing","datasets_with_task":"/datasets/task/monocular-cross-view-road-scene-parsing"}],"languages":[],"variants":["Argoverse","Argoverse CVPR 2020"],"data_loaders":[{"repo":"https://github.com/woodoxen/tactics2d","url":"https://tactics2d.readthedocs.io/en/latest/","frameworks":[]}],"num_papers_in_archive":386,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/motion-forecasting-on-argoverse-cvpr-2020","task":"Motion Forecasting","dataset_variant":"Argoverse CVPR 2020","rows":299,"metrics":["brier-minFDE (K=6)","minFDE (K=6)","MR (K=6)","minADE (K=6)","DAC (K=6)","minFDE (K=1)","MR (K=1)","minADE (K=1)"],"first_row_in_archive_order":{"model":"SEPT","paper":null,"metrics":{"DAC (K=6)":"0.9922","MR (K=1)":"0.5154","MR (K=6)":"0.1032","brier-minFDE (K=6)":"1.6820","minADE (K=1)":"1.4412","minADE (K=6)":"0.7282","minFDE (K=1)":"3.1777","minFDE (K=6)":"1.0566"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-object-tracking-on-argoverse-cvpr-2020","task":"3D Object Tracking","dataset_variant":"Argoverse CVPR 2020","rows":126,"metrics":["AVG-RANK"],"first_row_in_archive_order":{"model":"Alibaba_AD_Lab","paper":null,"metrics":{"AVG-RANK":"9.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-object-detection-on-argoverse","task":"3D Object Detection","dataset_variant":"Argoverse","rows":6,"metrics":["AVG-CDS"],"first_row_in_archive_order":{"model":"tempVar","paper":null,"metrics":{"AVG-CDS":"0.41"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/monocular-cross-view-road-scene-parsing-1","task":"Monocular Cross-View Road Scene Parsing(Vehicle)","dataset_variant":"Argoverse","rows":2,"metrics":["mAP","mIoU"],"first_row_in_archive_order":{"model":"DCTNet","paper":"/paper/a-dual-cycled-cross-view-transformer-network","metrics":{"mAP":"68.96%","mIoU":"48.04%"},"code_links":[{"title":"AutoCompSysLab/DCTNet","url":"https://github.com/AutoCompSysLab/DCTNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/monocular-cross-view-road-scene-parsing-road-2","task":"Monocular Cross-View Road Scene Parsing(Road)","dataset_variant":"Argoverse","rows":2,"metrics":["mAP","mIOU"],"first_row_in_archive_order":{"model":"DCTNet","paper":"/paper/a-dual-cycled-cross-view-transformer-network","metrics":{"mAP":"88.87%","mIOU":"76.71%"},"code_links":[{"title":"AutoCompSysLab/DCTNet","url":"https://github.com/AutoCompSysLab/DCTNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/trajectory-prediction-on-argoverse","task":"Trajectory Prediction","dataset_variant":"Argoverse","rows":1,"metrics":["MR (K=6)","brier-minFDE (K=6)","minADE (K=6)","minFDE (K=6)"],"first_row_in_archive_order":{"model":"HeteroGCN","paper":"/paper/dynamic-scenario-representation-learning-for","metrics":{"MR (K=6)":"0.12","brier-minFDE (K=6)":"1.75","minADE (K=6)":"0.79","minFDE (K=6)":"1.16"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/leveraging-future-relationship-reasoning-for","title":"Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction","date":"2023-05-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dynamic-scenario-representation-learning-for","title":"Dynamic Scenario Representation Learning for Motion Forecasting with Heterogeneous Graph Convolutional Recurrent Networks","date":"2023-03-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/query-centric-trajectory-prediction","title":"Query-Centric Trajectory Prediction","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/r-pred-two-stage-motion-prediction-via-tube","title":"R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement","date":"2022-11-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ganet-goal-area-network-for-motion","title":"GANet: Goal Area Network for Motion Forecasting","date":"2022-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-dual-cycled-cross-view-transformer-network","title":"A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird's-Eye-View","date":"2022-09-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/wayformer-motion-forecasting-via-simple","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","date":"2022-07-12","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/trajectory-forecasting-on-temporal-graphs","title":"Trajectory Forecasting on Temporal Graphs","date":"2022-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tenet-transformer-encoding-network-for","title":"TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction","date":"2022-06-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ssl-lanes-self-supervised-learning-for-motion","title":"SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving","date":"2022-06-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/holistic-transformer-a-joint-neural-network","title":"Holistic Transformer: A Joint Neural Network for Trajectory Prediction and Decision-Making of Autonomous Vehicles","date":"2022-06-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dcms-motion-forecasting-with-dual-consistency","title":"Bootstrap Motion Forecasting With Self-Consistent Constraints","date":"2022-04-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/crat-pred-vehicle-trajectory-prediction-with","title":"CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention","date":"2022-02-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hivt-hierarchical-vector-transformer-for","title":"HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction","date":"2022-01-01","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/multipath-efficient-information-fusion-and","title":"MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction","date":"2021-11-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/thomas-trajectory-heatmap-output-with-learned-1","title":"THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling","date":"2021-10-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gohome-graph-oriented-heatmap-output","title":"GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation","date":"2021-09-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/projecting-your-view-attentively-monocular","title":"Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View Transformation","date":"2021-06-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/home-heatmap-output-for-future-motion","title":"HOME: Heatmap Output for future Motion Estimation","date":"2021-05-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tpcn-temporal-point-cloud-networks-for-motion","title":"TPCN: Temporal Point Cloud Networks for Motion Forecasting","date":"2021-03-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lanercnn-distributed-representations-for","title":"LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting","date":"2021-01-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/prank-motion-prediction-based-on-ranking","title":"PRANK: motion Prediction based on RANKing","date":"2020-10-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tnt-target-driven-trajectory-prediction","title":"TNT: Target-driveN Trajectory Prediction","date":"2020-08-19","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}