Monocular 3D Human Pose Estimation with a Semi-supervised Graph-Based Method

Abbasi, Mahdieh; Rabiee, Hamid R.; Gagné, Christian

doi:10.1109/3dv.2015.64

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph-based semi-supervised learning (GSSL) methods have been successfully used in large number of applications [6][7][8][9][10][11][12][13][14] covering many application domains where labeling data is very expensive and time-consuming while unlabeled data is very cheap and easy to collect. The GSSL methods use an undirected graph to model the data set and the relationships among the data points.…”

Section: Graph-based Semi-supervised Learning Frameworkmentioning

confidence: 99%

“…Unlike those feature extraction based methods [2,38] or learning accurate features for face recognition [39][40][41], we use the raw pixels of 4096 dimensions directly with 64 × 64 resolution of every face image in ORL data set. 6 There are ten different images of each of 40 distinct persons in this face data set. For some persons, the images were taken at different times, varying the lighting, facial expressions (open/closed eyes, smiling/not smiling) and facial details (glasses/no glasses).…”

Section: Face Recognition Applicationmentioning

confidence: 99%

See 1 more Smart Citation

Random Multi-Graphs: A semi-supervised learning framework for classification of high dimensional data

Zhang¹,

Sun

Zhong

et al. 2017

Image and Vision Computing

View full text Add to dashboard Cite

A B S T R A C TCurrently, high dimensional data processing confronts two main difficulties: inefficient similarity measure and high computational complexity in both time and memory space. Common methods to deal with these two difficulties are based on dimensionality reduction and feature selection. In this paper, we present a different way to solve high dimensional data problems by combining the ideas of Random Forests and Anchor Graph semi-supervised learning. We randomly select a subset of features and use the Anchor Graph method to construct a graph. This process is repeated many times to obtain multiple graphs, a process which can be implemented in parallel to ensure runtime efficiency. Then the multiple graphs vote to determine the labels for the unlabeled data. We argue that the randomness can be viewed as a kind of regularization. We evaluate the proposed method on eight real-world data sets by comparing it with two traditional graphbased methods and one state-of-the-art semi-supervised learning method based on Anchor Graph to show its effectiveness. We also apply the proposed method to the subject of face recognition.

show abstract

Section: Graph-based Semi-supervised Learning Frameworkmentioning

confidence: 99%

Section: Face Recognition Applicationmentioning

confidence: 99%

Random Multi-Graphs: A semi-supervised learning framework for classification of high dimensional data

Zhang¹,

Sun

Zhong

et al. 2017

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Jain et al [51] were the first to use deep learning for features learning in human pose estimation. They utilized a multi-layer convolutional network to learn image features and spatial priors between parts as illustrated in Abbasi et al [75] proposed a semi-supervised graph-based approach to estimate 3D poses from a small set of labelled data. A frame sequence from the same activity (labelled and unlabelled) can be used to construct a graph model by finding its k-nearest neighbours (k-NN) and temporal relationships with consecutive frames.…”

Section: Deep Learning With Convolution Neural Networkmentioning

confidence: 99%