Abstract
Visual appearance score, appearance mixture type and deformation are three important information sources for human pose estimation. This paper proposes to build a multi-source deep model in order to extract non-linear representation from these different aspects of information sources. With the deep model, the global, high-order human body articulation patterns in these information sources are extracted for pose estimation. The task for estimating body locations and the task for human detection are jointly learned using a unified deep model. The proposed approach can be viewed as a post-processing of pose estimation results and can flexibly integrate with existing methods by taking their information sources as input. By extracting the non-linear representation from multiple information sources, the deep model outperforms state-of-the-art by up to 8.6 percent on three public benchmark datasets.
Keywords
Benchmark (surveying)Computer scienceArtificial intelligencePoseRepresentation (politics)Deep learningTask (project management)Machine learningPattern recognition (psychology)Task analysisEstimation
Affiliated Institutions
Related Publications
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
This paper considers the task of articulated human pose estimation of multiple people in real world images. We propose an approach that jointly solves the tasks of detection and...
Articulated people detection and pose estimation: Reshaping the future
State-of-the-art methods for human detection and pose estimation require many training samples for best performance. While large, manually collected datasets exist, the captured...
Deep High-Resolution Representation Learning for Human Pose Estimation
In this paper, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resol...
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
Human pose estimation has made significant progress during the last years. However current datasets are limited in their coverage of the overall pose estimation challenges. Stil...
DeepPose: Human Pose Estimation via Deep Neural Networks
We propose a method for human pose estimation based on Deep Neural Networks (DNNs). The pose estimation is formulated as a DNN-based regression problem towards body joints. We p...
Publication Info
- Year
- 2014
- Type
- article
- Pages
- 2337-2344
- Citations
- 273
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
273
OpenAlex
Cite This
Wanli Ouyang,
Xiao Chu,
Xiaogang Wang
(2014).
Multi-source Deep Learning for Human Pose Estimation.
, 2337-2344.
https://doi.org/10.1109/cvpr.2014.299
Identifiers
- DOI
- 10.1109/cvpr.2014.299