[PDF][PDF] Training data generation based on observation probability density for human pose refinement
K Oniki, T Kikuchi, Y Ozasa - Journal of Image and …, 2021 - pdfs.semanticscholar.org
K Oniki, T Kikuchi, Y Ozasa
Journal of Image and Graphics, 2021•pdfs.semanticscholar.orgHuman pose estimation is an active research topic since for decades, and it has immediate
applications in various tasks such as action understanding. Although accurate pose
estimation is an important requirement, joint occlusion and various gestures of a person
often result in deviated pose predictions. In this paper, we aim to correct such outliers
included in pose estimation results. We propose a method to generate training data which is
effective for learning models for outlier correction.
applications in various tasks such as action understanding. Although accurate pose
estimation is an important requirement, joint occlusion and various gestures of a person
often result in deviated pose predictions. In this paper, we aim to correct such outliers
included in pose estimation results. We propose a method to generate training data which is
effective for learning models for outlier correction.
Abstract
Human pose estimation is an active research topic since for decades, and it has immediate applications in various tasks such as action understanding. Although accurate pose estimation is an important requirement, joint occlusion and various gestures of a person often result in deviated pose predictions. In this paper, we aim to correct such outliers included in pose estimation results. We propose a method to generate training data which is effective for learning models for outlier correction.
pdfs.semanticscholar.org