DMCA
Pose Machines: Articulated Pose Estimation via Inference Machines
| Citations: | 1 - 0 self |
BibTeX
@MISC{Ramakrishna_posemachines:,
author = {Varun Ramakrishna and Daniel Munoz and Martial Hebert and J. Andrew Bagnell and Yaser Sheikh},
title = {Pose Machines: Articulated Pose Estimation via Inference Machines},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. State-of-the-art approaches for articulated human pose es-timation are rooted in parts-based graphical models. These models are often restricted to tree-structured representations and simple parametric potentials in order to enable tractable inference. However, these simple dependencies fail to capture all the interactions between body parts. While models with more complex interactions can be defined, learning the parameters of these models remains challenging with intractable or approximate inference. In this paper, instead of performing inference on a learned graphical model, we build upon the inference machine frame-work and present a method for articulated human pose estimation. Our approach incorporates rich spatial interactions among multiple parts and information across parts of different scales. Additionally, the modular framework of our approach enables both ease of implementation with-out specialized optimization solvers, and efficient inference. We analyze our approach on two challenging datasets with large pose variation and outperform the state-of-the-art on these benchmarks. 1
Keyphrases
pose machine pose estimation inference machine articulated human pose estimation modular framework state-of-the-art approach learned graphical model rich spatial interaction efficient inference implementation with-out specialized optimization solver complex interaction different scale parts-based graphical model large pose variation tractable inference articulated human pose es-timation approximate inference multiple part simple parametric potential simple dependency tree-structured representation inference machine frame-work body part
