A Bayesian Framework for Sparse Representation-Based 3-D Human Pose Estimation

Babagholami-Mohamadabadi, Behnam; Jourabloo, Amin; Zarghami, Ali; Kasaei, Shohreh

doi:10.1109/lsp.2014.2301726

Cited by 20 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [163] present a CNN that involves training an Regions with CNN features (R-CNN) detector with loss functions. The authors of [164] adopt an iterative error feedback that changes an initial solution by feeding back error predictions. Exemplar-Based Methods The exemplar-based approaches estimate the pose of an unknown visual input image [118] based on a discrete set of specific poses with their corresponding representations [160]. Randomized trees [165] and random forests [166,167] are fast and robust classification techniques that can handle this type of problem [266].…”

Section: Methodologiesmentioning

confidence: 99%

“…The exemplar-based approaches estimate the pose of an unknown visual input image [118] based on a discrete set of specific poses with their corresponding representations [160]. Randomized trees [165] and random forests [166,167] are fast and robust classification techniques that can handle this type of problem [266].…”

Section: Methodologiesmentioning

confidence: 99%

“…Generative approaches [22,114,115,116,117,118,119] model the likelihood of the observations given a pose estimate. Inference involves a complex search over the state space to locate the peaks of the likelihood [128].…”

Section: Methodologiesmentioning

confidence: 99%

See 2 more Smart Citations

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Gong

Zhang

Gonzàlez

et al. 2016

Sensors

130

View full text Add to dashboard Cite

Human pose estimation refers to the estimation of the location of body parts and how they are connected in an image. Human pose estimation from monocular images has wide applications (e.g., image indexing). Several surveys on human pose estimation can be found in the literature, but they focus on a certain category; for example, model-based approaches or human motion analysis, etc. As far as we know, an overall review of this problem domain has yet to be provided. Furthermore, recent advancements based on deep learning have brought novel algorithms for this problem. In this paper, a comprehensive survey of human pose estimation from monocular images is carried out including milestone works and recent advancements. Based on one standard pipeline for the solution of computer vision problems, this survey splits the problem into several modules: feature extraction and description, human body models, and modeling methods. Problem modeling methods are approached based on two means of categorization in this survey. One way to categorize includes top-down and bottom-up methods, and another way includes generative and discriminative methods. Considering the fact that one direct application of human pose estimation is to provide initialization for automatic video surveillance, there are additional sections for motion-related methods in all modules: motion features, motion models, and motion-based methods. Finally, the paper also collects 26 publicly available data sets for validation and provides error measurement methods that are frequently used.

show abstract

Section: Methodologiesmentioning

confidence: 99%

Section: Methodologiesmentioning

confidence: 99%

See 1 more Smart Citation

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Gong

Zhang

Gonzàlez

et al. 2016

Sensors

130

View full text Add to dashboard Cite

show abstract

“…However, directly obtaining the posterior distributions is not computationally feasible and results in explosive number of probability factors growing exponentially with number of coefficients. To handle the intractable integrals of the inference procedure, variational inference is often employed [17][18][19].…”

Section: Bayesian Inference Of Importance Levelsmentioning

confidence: 99%

Adaptive non-uniform compressive sampling for time-varying signals

Zaeemzadeh

Joneidi

Rahnavard

2017

2017 51st Annual Conference on Information Sciences and Systems (CISS)

View full text Add to dashboard Cite

In this paper, adaptive non-uniform compressive sampling (ANCS) of time-varying signals, which are sparse in a proper basis, is introduced. ANCS employs the measurements of previous time steps to distribute the sensing energy among coefficients more intelligently. To this aim, a Bayesian inference method is proposed that does not require any prior knowledge of importance levels of coefficients or sparsity of the signal. Our numerical simulations show that ANCS is able to achieve the desired non-uniform recovery of the signal. Moreover, if the signal is sparse in canonical basis, ANCS can reduce the number of required measurements significantly.

show abstract

“…So, in this method, a test sample is represented as the linear combination of the original training samples (the training samples are considered as the dictionary atoms), and the reconstruction error over each class is used as a measure to classify the test sample. The sparse representation is successfully utilized in many other applications of computer vision [3,32], which shows that it is a proven method for classification and regression problems.…”

Section: Introductionmentioning

confidence: 99%

A novel sparse coding algorithm for classification of tumors based on gene expression data

Khormuji

Bazrafkan

2015

Med Biol Eng Comput

View full text Add to dashboard Cite

High-dimensional genomic and proteomic data play an important role in many applications in medicine such as prognosis of diseases, diagnosis, prevention and molecular biology, to name a few. Classifying such data is a challenging task due to the various issues such as curse of dimensionality, noise and redundancy. Recently, some researchers have used the sparse representation (SR) techniques to analyze high-dimensional biological data in various applications in classification of cancer patients based on gene expression datasets. A common problem with all SR-based biological data classification methods is that they cannot utilize the topological (geometrical) structure of data. More precisely, these methods transfer the data into sparse feature space without preserving the local structure of data points. In this paper, we proposed a novel SR-based cancer classification algorithm based on gene expression data that takes into account the geometrical information of all data. Precisely speaking, we incorporate the local linear embedding algorithm into the sparse coding framework, by which we can preserve the geometrical structure of all data. For performance comparison, we applied our algorithm on six tumor gene expression datasets, by which we demonstrate that the proposed method achieves higher classification accuracy than state-of-the-art SR-based tumor classification algorithms.

show abstract

A Bayesian Framework for Sparse Representation-Based 3-D Human Pose Estimation

Cited by 20 publications

References 11 publications

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Adaptive non-uniform compressive sampling for time-varying signals

A novel sparse coding algorithm for classification of tumors based on gene expression data

Contact Info

Product

Resources

About