Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 45, Issue 4, Pages 5296-5313Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2022.3197352
Keywords
Pose estimation; Computer architecture; Location awareness; Neural networks; Three-dimensional displays; Solid modeling; Task analysis; Whole-body human pose estimation; neural architecture search; in-the-wild dataset
Ask authors/readers for more resources
This paper investigates the task of 2D whole-body human pose estimation and proposes the ZoomNet approach to localize dense landmarks on the entire human body. The ZoomNet approach considers the hierarchical structure and scale variation of different body parts. The authors also propose the ZoomNAS framework for neural architecture search to improve the accuracy and efficiency of whole-body pose estimation.
This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts. We further propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation. ZoomNAS jointly searches the model architecture and the connections between different sub-modules, and automatically allocates computational complexity for searched sub-modules. To train and evaluate ZoomNAS, we introduce the first large-scale 2D human whole-body dataset, namely COCO-WholeBody V1.0, which annotates 133 keypoints for in-the-wild images. Extensive experiments demonstrate the effectiveness of ZoomNAS and the significance of COCO-WholeBody V1.0.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available