Discriminative Generative Contour Detection

Zhang, Chao; Li, Xiong; Ruan, Xiang; Zhao, Yuming; Yang, Ming–Hsuan

doi:10.5244/c.27.74

Cited by 5 publications

(3 citation statements)

References 21 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(11) exploit the additional information contained in the hidden variable z. This information usually represents higher level concepts hid in the observed random variables, like the cluster or mixture center in image representation using the bag-of-words model [22].…”

Section: Free Energy Score Space Encodingmentioning

confidence: 99%

Person re-identification by free energy score space encoding

Zhao

Liu

2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Person re-identification is an important and challenging computer vision problem. Recent progress in this area is due to new visual features and models that deals with crossview variations. Instead of working towards more complex models, we focus on low level features and their encoding. Low level features capturing the color and structural information are first extracted from human images. Gaussian Mixture Model (GMM) is then employed to approximate the distribution of the features, providing a relatively comprehensive statistical representation. Finally, low level features are mapped to a space by computing free energy score of the GMM. The mapped features are encoded into a fixed-length feature vector for person re-identification. Extensive experiments are conducted on several public datasets. Comparisons with benchmark person re-identification methods show the promising performance of our approach.Index Terms-person re-identification, appearance modeling, Gaussian Mixture Model, free energy score space

show abstract

Section: Free Energy Score Space Encodingmentioning

confidence: 99%

Person re-identification by free energy score space encoding

Zhao

Liu

2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…: Assume that , and are ¿xed, the optimal can be obtained by minimizing the following optimization problem: (16) We still adopt the graphical Lasso procedure to solve the standard inverse covariance estimation problem with sample covariance of .…”

Section: Updatementioning

confidence: 99%

“…The posterior distribution for , which is proportional to the product of the prior and the likelihood function [15], [16], [17], is de¿ned by:…”

Section: A Formulationmentioning

confidence: 99%

Multiple-Output Regression with High-Order Structure Information

Yang

Liu

et al. 2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

In this paper, we propose a new method to learn the regression coef¿cient matrix for multiple-output regression, which is inspired by multi-task learning. We attempt to incorporate high-order structure information among the regression coef¿-cients into the estimated process of regression coef¿cient matrix, which is of great importance for multiple-output regression. Meanwhile, we also intend to describe the output structure with noise covariance matrix to assist in learning model parameters. Taking account of the real-world data often corrupted by noise, we place a constraint of minimizing norm on regression coef¿cient matrix to make it robust to noise. The experiments are conducted on three public available datasets, and the experimental results demonstrate the power of the proposed method against the state-of-the-art methods.

show abstract

Digital IIR Filter Design with Fix-Point Representation Using Effective Evolutionary Local Search Enhanced Differential Evolution

Wang

Dong

Yan

et al. 2015

Computational Intelligence in Digital and Network Designs and Applications

Self Cite

View full text Add to dashboard Cite

Previously, the parameters of digital IIR filters were encoded with floatingpoint representations. It is known that a fixed-point representation can effectively save computational resources and is more convenient for direct realization on hardware. Inherently, compared with floating-point representation, fixed-point representation may make the search space miss much useful gradient information and, therefore, raises new challenges. In this chapter, the universality of DE-based MA is improved by implementing more efficient evolutionary algorithms (EAs) as the local search techniques. The performance of the newly designed algorithm is experimentally verified in both function optimization tasks and digital IIR filter design problems.

show abstract

Discriminative Generative Contour Detection

Cited by 5 publications

References 21 publications

Person re-identification by free energy score space encoding

Person re-identification by free energy score space encoding

Multiple-Output Regression with High-Order Structure Information

Digital IIR Filter Design with Fix-Point Representation Using Effective Evolutionary Local Search Enhanced Differential Evolution

Contact Info

Product

Resources

About