Research map / 3D vision / Human pose estimation
JRDB-Pose: A Large-Scale Dataset for Multi-Person Pose Estimation and Tracking
Edward Vendrow, Duy Tho Le, Jianfei Cai, Hamid Rezatofighi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use YOLO-Pose instead of the other evaluated pose estimators | Multi-person pose estimation · JRDB-Pose stitched | OSPA-Pose: 0.480 -> 0.368 | Improved |
| Use YOLO-Pose instead of the other evaluated pose estimators | Multi-person pose estimation · JRDB-Pose stitched | AP: 24.6 -> 47.9 | Improved |
| Use OCTrack rather than ByteTrack or UniTrack | YOLO-Pose tracking predictions · JRDB-Pose individual camera images | OSPA²-Pose: 0.715 -> 0.630; 0.727 -> 0.630; 0.693 -> 0.577; 0.725 -> 0.577; 0.690 -> 0.594; 0.708 -> 0.594 | Improved |
| Fine-tune COCO-pretrained weights on JRDB-Pose rather than use COCO weights without fine-tuning (ablation) | YOLO-Pose · JRDB-Pose stitched | AP: 48.0 -> 49.6 | Improved |
| Fine-tune COCO-pretrained weights on JRDB-Pose rather than use COCO weights without fine-tuning (ablation) | YOLO-Pose · JRDB-Pose stitched | OSPA-Pose: 0.460 -> 0.385 | Improved |
| Fine-tune COCO-pretrained weights on JRDB-Pose rather than use COCO weights without fine-tuning (ablation) | YOLO-Pose · JRDB-Pose per camera | AP: 60.2 -> 63.9 | Improved |
| Fine-tune COCO-pretrained weights on JRDB-Pose rather than use COCO weights without fine-tuning (ablation) | YOLO-Pose · JRDB-Pose per camera | OSPA-Pose: 0.320 -> 0.273 | Improved |
| Fine-tune COCO-pretrained weights on JRDB-Pose rather than train from scratch (ablation) | YOLO-Pose · JRDB-Pose stitched | OSPA-Pose: 0.357 -> 0.385 | Hurt |
| Fine-tune COCO-pretrained weights on JRDB-Pose rather than train from scratch (ablation) | YOLO-Pose · JRDB-Pose per camera | OSPA-Pose: 0.280 -> 0.273 | Improved |
Closest papers by meaning
- PoseTrack: A Benchmark for Human Pose Estimation and Tracking (CVPR 2018 · similarity 0.90)
- JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups (CVPR 2024 · similarity 0.89)
- JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments (TPAMI 2021 · similarity 0.89)
- JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments (CVPR 2024 · similarity 0.87)
- FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions (CVPR 2024 · similarity 0.87)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
