COCO test-dev

Emerging

2papers using it

2020first seen

The 'COCO test-dev' dataset is a benchmark that contains images used to evaluate the performance of multi-person pose estimation methods, specifically measuring their accuracy in detecting and associating keypoints for individual instances in complex scenes.

🔎 Find this dataset

Papers using COCO test-dev (2)

BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation2023 · 1 cites

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution2020 · 155 cites