AI Paper Atlas

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

CVPR 2023 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 28 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use YOLO-Pose instead of the other evaluated pose estimatorsMulti-person pose estimation · JRDB-Pose stitchedOSPA-Pose: 0.480 -> 0.368Improved
Use YOLO-Pose instead of the other evaluated pose estimatorsMulti-person pose estimation · JRDB-Pose stitchedAP: 24.6 -> 47.9Improved
Use OCTrack rather than ByteTrack or UniTrackYOLO-Pose tracking predictions · JRDB-Pose individual camera imagesOSPA²-Pose: 0.715 -> 0.630; 0.727 -> 0.630; 0.693 -> 0.577; 0.725 -> 0.577; 0.690 -> 0.594; 0.708 -> 0.594Improved
Fine-tune COCO-pretrained weights on JRDB-Pose rather than use COCO weights without fine-tuning (ablation)YOLO-Pose · JRDB-Pose stitchedAP: 48.0 -> 49.6Improved
Fine-tune COCO-pretrained weights on JRDB-Pose rather than use COCO weights without fine-tuning (ablation)YOLO-Pose · JRDB-Pose stitchedOSPA-Pose: 0.460 -> 0.385Improved
Fine-tune COCO-pretrained weights on JRDB-Pose rather than use COCO weights without fine-tuning (ablation)YOLO-Pose · JRDB-Pose per cameraAP: 60.2 -> 63.9Improved
Fine-tune COCO-pretrained weights on JRDB-Pose rather than use COCO weights without fine-tuning (ablation)YOLO-Pose · JRDB-Pose per cameraOSPA-Pose: 0.320 -> 0.273Improved
Fine-tune COCO-pretrained weights on JRDB-Pose rather than train from scratch (ablation)YOLO-Pose · JRDB-Pose stitchedOSPA-Pose: 0.357 -> 0.385Hurt
Fine-tune COCO-pretrained weights on JRDB-Pose rather than train from scratch (ablation)YOLO-Pose · JRDB-Pose per cameraOSPA-Pose: 0.280 -> 0.273Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy