{"url":"/dataset/argoverse-hd","name":"Argoverse-HD","full_name":null,"description_markdown":"[Argoverse-HD](https://www.cs.cmu.edu/~mengtial/proj/streaming/) is a dataset built for streaming object detection, which encompasses real-time object detection, video object detection, tracking, and short-term forecasting. It contains the video data from [Argoverse 1.1](https://www.argoverse.org/av1.html) with our own MS COCO-style bounding box annotations with track IDs. The annotations are backward-compatible with COCO as one can directly evaluate COCO pre-trained models on this dataset to estimate the efficiency or the cross-dataset generalization capability of the models. The dataset contains **high-quality and temporally-dense annotations for high-resolution videos** (1920 x 1200 @ 30 FPS). Overall, there are 70,000 image frames and 1.3 million bounding boxes.\r\n\r\nArgoverse-HD is the dataset used in the [Streaming Perception Challenge](https://eval.ai/web/challenges/challenge-page/800/overview), which includes two tracks:\r\n\r\n- **Detection-only (real-time object detection)**. In this track, the participants will develop single-frame object detectors as they would for COCO and LVIS challenges. The crucial distinction is that the evaluation will score latency through streaming accuracy.\r\n- **Full-stack**. In this track, the method is unrestricted. However, most likely tracking and forecasting will be used to compensate for the latency of the detectors.\r\n\r\nBy default, all submissions measure their latency on a V100 GPU with the [official toolkit](https://github.com/karthiksharma98/sap-starterkit).","description_withheld":null,"homepage":"https://www.cs.cmu.edu/~mengtial/proj/streaming/","introduced_date":"2020-05-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/towards-streaming-image-understanding","title":"Towards Streaming Perception","first_author":"Mengtian Li","url":null},"license":{"name":"MIT","url":"https://github.com/mtli/sAP/blob/master/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Real-Time Object Detection","url":"/task/real-time-object-detection","datasets_with_task":"/datasets/task/real-time-object-detection"},{"name":"Motion Forecasting","url":"/task/motion-forecasting","datasets_with_task":"/datasets/task/motion-forecasting"},{"name":"Real-Time Multi-Object Tracking","url":"/task/real-time-multi-object-tracking","datasets_with_task":"/datasets/task/real-time-multi-object-tracking"}],"languages":[],"variants":["Argoverse-HD (Full-Stack, Test)","Argoverse-HD (Full-Stack, Val)","Argoverse-HD (Detection-Only, Test)","Argoverse-HD (Detection-Only, Val)","Argoverse-HD Val (Detection-Only)","Full-Stack (Val Set)","Detection-Only (Val Set)","Full-Stack (Test Set)","Detection-Only (Test Set)","Argoverse-HD"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/real-time-object-detection-on-argoverse-hd-4","task":"Real-Time Object Detection","dataset_variant":"Argoverse-HD (Full-Stack, Val)","rows":4,"metrics":["AP","sAP"],"first_row_in_archive_order":{"model":"RL-Based Dynamic-Online Policy","paper":null,"metrics":{"AP":"26.01"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/real-time-object-detection-on-argoverse-hd-3","task":"Real-Time Object Detection","dataset_variant":"Argoverse-HD (Detection-Only, Test)","rows":3,"metrics":["AP"],"first_row_in_archive_order":{"model":"YOLOX","paper":"/paper/yolox-exceeding-yolo-series-in-2021","metrics":{"AP":"41.1"},"code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"Megvii-BaseDetection/YOLOX","url":"https://github.com/Megvii-BaseDetection/YOLOX"},{"title":"Deci-AI/super-gradients","url":"https://github.com/Deci-AI/super-gradients"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/yolox"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"qy1994-0919/cfpnet","url":"https://github.com/qy1994-0919/cfpnet"},{"title":"texasinstruments/edgeai-yolox","url":"https://github.com/texasinstruments/edgeai-yolox"},{"title":"wangdongdut/dut-anti-uav","url":"https://github.com/wangdongdut/dut-anti-uav"},{"title":"MegEngine/YOLOX","url":"https://github.com/MegEngine/YOLOX"},{"title":"zhangming8/yolox-pytorch","url":"https://github.com/zhangming8/yolox-pytorch"},{"title":"NEUAutonomousDriving408/CIVCAutonomousDriving","url":"https://github.com/NEUAutonomousDriving408/CIVCAutonomousDriving"},{"title":"DataXujing/YOLOX-","url":"https://github.com/DataXujing/YOLOX-"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"jinsheng124/yolox","url":"https://github.com/jinsheng124/yolox"},{"title":"apolloauto/apollo-model-yolox","url":"https://github.com/apolloauto/apollo-model-yolox"},{"title":"jesse01/paddle-yolox","url":"https://github.com/jesse01/paddle-yolox"},{"title":"middleprince/YOLOX-SS","url":"https://github.com/middleprince/YOLOX-SS"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/res2net_yolov3"},{"title":"chenyicai-0611/YOLOX-Flask-deployment","url":"https://github.com/chenyicai-0611/YOLOX-Flask-deployment"},{"title":"lazyn1997/YOLOX","url":"https://github.com/lazyn1997/YOLOX"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/YOLOX"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/YOLOv3"},{"title":"newsun-boki/yolox-openvino-video-infer","url":"https://github.com/newsun-boki/yolox-openvino-video-infer"},{"title":"newsun-boki/yolovx-openvino-c--video-infer","url":"https://github.com/newsun-boki/yolovx-openvino-c--video-infer"},{"title":"liuyuan000/yolox_sar","url":"https://github.com/liuyuan000/yolox_sar"},{"title":"2023-MindSpore-1/ms-code-182","url":"https://github.com/2023-MindSpore-1/ms-code-182"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/YOLOX"},{"title":"xiyie/yolox","url":"https://github.com/xiyie/yolox"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/res2net_yolov3"},{"title":"pmj110119/yolox","url":"https://github.com/pmj110119/yolox"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/res2net_yolov3"},{"title":"mszpc/yolox","url":"https://github.com/mszpc/yolox"},{"title":"pistachio0812/YOLOX","url":"https://github.com/pistachio0812/YOLOX"},{"title":"2023-MindSpore-1/ms-code-194","url":"https://github.com/2023-MindSpore-1/ms-code-194"},{"title":"2023-MindSpore-1/ms-code-191","url":"https://github.com/2023-MindSpore-1/ms-code-191"},{"title":"kisna-aryan/YOLOX","url":"https://github.com/kisna-aryan/YOLOX"},{"title":"StephenStorm/YOLOX","url":"https://github.com/StephenStorm/YOLOX"},{"title":"2023-MindSpore-1/ms-code-31","url":"https://github.com/2023-MindSpore-1/ms-code-31"},{"title":"arnavr.neo/YOLOX","url":"https://dagshub.com/arnavr.neo/YOLOX"},{"title":"gloria111/YOLOX_paddle","url":"https://github.com/gloria111/YOLOX_paddle"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/real-time-object-detection-on-argoverse-hd-5","task":"Real-Time Object Detection","dataset_variant":"Argoverse-HD (Full-Stack, Test)","rows":3,"metrics":["AP"],"first_row_in_archive_order":{"model":"YOLOX","paper":"/paper/yolox-exceeding-yolo-series-in-2021","metrics":{"AP":"41.1"},"code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"Megvii-BaseDetection/YOLOX","url":"https://github.com/Megvii-BaseDetection/YOLOX"},{"title":"Deci-AI/super-gradients","url":"https://github.com/Deci-AI/super-gradients"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/yolox"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"qy1994-0919/cfpnet","url":"https://github.com/qy1994-0919/cfpnet"},{"title":"texasinstruments/edgeai-yolox","url":"https://github.com/texasinstruments/edgeai-yolox"},{"title":"wangdongdut/dut-anti-uav","url":"https://github.com/wangdongdut/dut-anti-uav"},{"title":"MegEngine/YOLOX","url":"https://github.com/MegEngine/YOLOX"},{"title":"zhangming8/yolox-pytorch","url":"https://github.com/zhangming8/yolox-pytorch"},{"title":"NEUAutonomousDriving408/CIVCAutonomousDriving","url":"https://github.com/NEUAutonomousDriving408/CIVCAutonomousDriving"},{"title":"DataXujing/YOLOX-","url":"https://github.com/DataXujing/YOLOX-"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"jinsheng124/yolox","url":"https://github.com/jinsheng124/yolox"},{"title":"apolloauto/apollo-model-yolox","url":"https://github.com/apolloauto/apollo-model-yolox"},{"title":"jesse01/paddle-yolox","url":"https://github.com/jesse01/paddle-yolox"},{"title":"middleprince/YOLOX-SS","url":"https://github.com/middleprince/YOLOX-SS"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/res2net_yolov3"},{"title":"chenyicai-0611/YOLOX-Flask-deployment","url":"https://github.com/chenyicai-0611/YOLOX-Flask-deployment"},{"title":"lazyn1997/YOLOX","url":"https://github.com/lazyn1997/YOLOX"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/YOLOX"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/YOLOv3"},{"title":"newsun-boki/yolox-openvino-video-infer","url":"https://github.com/newsun-boki/yolox-openvino-video-infer"},{"title":"newsun-boki/yolovx-openvino-c--video-infer","url":"https://github.com/newsun-boki/yolovx-openvino-c--video-infer"},{"title":"liuyuan000/yolox_sar","url":"https://github.com/liuyuan000/yolox_sar"},{"title":"2023-MindSpore-1/ms-code-182","url":"https://github.com/2023-MindSpore-1/ms-code-182"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/YOLOX"},{"title":"xiyie/yolox","url":"https://github.com/xiyie/yolox"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/res2net_yolov3"},{"title":"pmj110119/yolox","url":"https://github.com/pmj110119/yolox"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/res2net_yolov3"},{"title":"mszpc/yolox","url":"https://github.com/mszpc/yolox"},{"title":"pistachio0812/YOLOX","url":"https://github.com/pistachio0812/YOLOX"},{"title":"2023-MindSpore-1/ms-code-194","url":"https://github.com/2023-MindSpore-1/ms-code-194"},{"title":"2023-MindSpore-1/ms-code-191","url":"https://github.com/2023-MindSpore-1/ms-code-191"},{"title":"kisna-aryan/YOLOX","url":"https://github.com/kisna-aryan/YOLOX"},{"title":"StephenStorm/YOLOX","url":"https://github.com/StephenStorm/YOLOX"},{"title":"2023-MindSpore-1/ms-code-31","url":"https://github.com/2023-MindSpore-1/ms-code-31"},{"title":"arnavr.neo/YOLOX","url":"https://dagshub.com/arnavr.neo/YOLOX"},{"title":"gloria111/YOLOX_paddle","url":"https://github.com/gloria111/YOLOX_paddle"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/real-time-object-detection-on-argoverse-hd-2","task":"Real-Time Object Detection","dataset_variant":"Argoverse-HD (Detection-Only, Val)","rows":2,"metrics":["AP"],"first_row_in_archive_order":{"model":"YOLOX","paper":"/paper/yolox-exceeding-yolo-series-in-2021","metrics":{"AP":"47.42"},"code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"Megvii-BaseDetection/YOLOX","url":"https://github.com/Megvii-BaseDetection/YOLOX"},{"title":"Deci-AI/super-gradients","url":"https://github.com/Deci-AI/super-gradients"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/yolox"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"qy1994-0919/cfpnet","url":"https://github.com/qy1994-0919/cfpnet"},{"title":"texasinstruments/edgeai-yolox","url":"https://github.com/texasinstruments/edgeai-yolox"},{"title":"wangdongdut/dut-anti-uav","url":"https://github.com/wangdongdut/dut-anti-uav"},{"title":"MegEngine/YOLOX","url":"https://github.com/MegEngine/YOLOX"},{"title":"zhangming8/yolox-pytorch","url":"https://github.com/zhangming8/yolox-pytorch"},{"title":"NEUAutonomousDriving408/CIVCAutonomousDriving","url":"https://github.com/NEUAutonomousDriving408/CIVCAutonomousDriving"},{"title":"DataXujing/YOLOX-","url":"https://github.com/DataXujing/YOLOX-"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"jinsheng124/yolox","url":"https://github.com/jinsheng124/yolox"},{"title":"apolloauto/apollo-model-yolox","url":"https://github.com/apolloauto/apollo-model-yolox"},{"title":"jesse01/paddle-yolox","url":"https://github.com/jesse01/paddle-yolox"},{"title":"middleprince/YOLOX-SS","url":"https://github.com/middleprince/YOLOX-SS"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/res2net_yolov3"},{"title":"chenyicai-0611/YOLOX-Flask-deployment","url":"https://github.com/chenyicai-0611/YOLOX-Flask-deployment"},{"title":"lazyn1997/YOLOX","url":"https://github.com/lazyn1997/YOLOX"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/YOLOX"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/YOLOv3"},{"title":"newsun-boki/yolox-openvino-video-infer","url":"https://github.com/newsun-boki/yolox-openvino-video-infer"},{"title":"newsun-boki/yolovx-openvino-c--video-infer","url":"https://github.com/newsun-boki/yolovx-openvino-c--video-infer"},{"title":"liuyuan000/yolox_sar","url":"https://github.com/liuyuan000/yolox_sar"},{"title":"2023-MindSpore-1/ms-code-182","url":"https://github.com/2023-MindSpore-1/ms-code-182"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/YOLOX"},{"title":"xiyie/yolox","url":"https://github.com/xiyie/yolox"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/res2net_yolov3"},{"title":"pmj110119/yolox","url":"https://github.com/pmj110119/yolox"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/res2net_yolov3"},{"title":"mszpc/yolox","url":"https://github.com/mszpc/yolox"},{"title":"pistachio0812/YOLOX","url":"https://github.com/pistachio0812/YOLOX"},{"title":"2023-MindSpore-1/ms-code-194","url":"https://github.com/2023-MindSpore-1/ms-code-194"},{"title":"2023-MindSpore-1/ms-code-191","url":"https://github.com/2023-MindSpore-1/ms-code-191"},{"title":"kisna-aryan/YOLOX","url":"https://github.com/kisna-aryan/YOLOX"},{"title":"StephenStorm/YOLOX","url":"https://github.com/StephenStorm/YOLOX"},{"title":"2023-MindSpore-1/ms-code-31","url":"https://github.com/2023-MindSpore-1/ms-code-31"},{"title":"arnavr.neo/YOLOX","url":"https://dagshub.com/arnavr.neo/YOLOX"},{"title":"gloria111/YOLOX_paddle","url":"https://github.com/gloria111/YOLOX_paddle"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dade-delay-adoptive-detector-for-streaming","title":"DaDe: Delay-adaptive Detector for Streaming Perception","date":"2022-12-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-time-object-detection-for-streaming","title":"Real-time Object Detection for Streaming Perception","date":"2022-03-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/yolox-exceeding-yolo-series-in-2021","title":"YOLOX: Exceeding YOLO Series in 2021","date":"2021-07-18","rows_on_this_dataset":3,"code_links":42,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":23,"samples_ran":1,"samples_unverified":22,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-streaming-image-understanding","title":"Towards Streaming Perception","date":"2020-05-21","rows_on_this_dataset":4,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":25,"samples_ran":1,"samples_unverified":24,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}