COCO-WholeBody dataset is the first large-scale benchmark for whole-body pose es

Deep Learning/Papers2read 2020. 7. 29. 16:24

COCO-WholeBody dataset is the first large-scale benchmark for whole-body pose estimation. It is an extension of COCO 2017 dataset with the same train/val split as COCO.

For project and code/API/expert requests: https://www.catalyzex.com/paper/arxiv:2007.11858

For each person, they annotate 4 types of bounding boxes (person box, face box, left-hand box, and right-hand box) and 133 keypoints (17 for body, 6 for feet, 68 for face and 42 for hands).

Get the free ML code finder browser extension:
Chrome https://bit.ly/code_finder_chrome
Firefox https://bit.ly/code_finder_firefox.

'Deep Learning > Papers2read' 카테고리의 다른 글

A novel neural network to generate high-resolution images For project and code/A (0)	2020.08.27
# 질문 있습니다! 첨부한 파일은 성별 전환 애플리케이션(Application)으로 레오나르도 디카프리오(Leonardo DiCaprio)의 (0)	2020.08.05
Latest from Stanford and Adobe Researchers: Inferring 3D human motion from video (0)	2020.07.25
Latest from Max Planck researchers: State of the art in Shape and Pose Disentang (0)	2020.07.24
From #ECCV2020: Reconstruct a morphable shape, texture, and viewpoint from an i (0)	2020.07.24