Sorry, you need to enable JavaScript to visit this website.

Bioinformatics

Face Recognition with Disentangled Facial Representation Learning and Data Augmentation


We address two issues for tackling face recognition across pose, one is disentangled representation learning and the other is training data augmentation. To have better training properties, we propose the Representation-Learning Wasserstein-GAN (RL-WGAN) with three component networks for learning the disentangled facial representation. As the learning based on imbalanced data often leads to biased estimation, we proposed a data augmentation scheme that exploits the 3D Morphable Model (3DMM) for generating faces of desired poses.

Paper Details

Authors:
Submitted On:
19 September 2019 - 6:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_Poster.pdf

(17)

Keywords

Subscribe

[1] , "Face Recognition with Disentangled Facial Representation Learning and Data Augmentation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4721. Accessed: Oct. 22, 2019.
@article{4721-19,
url = {http://sigport.org/4721},
author = { },
publisher = {IEEE SigPort},
title = {Face Recognition with Disentangled Facial Representation Learning and Data Augmentation},
year = {2019} }
TY - EJOUR
T1 - Face Recognition with Disentangled Facial Representation Learning and Data Augmentation
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4721
ER -
. (2019). Face Recognition with Disentangled Facial Representation Learning and Data Augmentation. IEEE SigPort. http://sigport.org/4721
, 2019. Face Recognition with Disentangled Facial Representation Learning and Data Augmentation. Available at: http://sigport.org/4721.
. (2019). "Face Recognition with Disentangled Facial Representation Learning and Data Augmentation." Web.
1. . Face Recognition with Disentangled Facial Representation Learning and Data Augmentation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4721

Thermal Face Recognition based on Physiological Information


In this paper, we propose a novel thermal face recognition based on physiological information. The training phase includes preprocessing, feature extraction and classification. In the beginning, the human face can be depicted from the background of thermal image using the Bayesian framework and normalized to uniform size. A grid of 22 thermal points is extracted as a feature vector. These 22 extracted points are used to train Linear Support Vector Machine Classifier (linear SVC). The classifier calculates the support vectors and uses them to find the hyperplane for classification.

Paper Details

Authors:
Shinfeng D. Lin, Kuanyuan Chen, Wensheng Chen
Submitted On:
18 September 2019 - 9:04am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019 poster_20190925.pdf

(9)

Keywords

Additional Categories

Subscribe

[1] Shinfeng D. Lin, Kuanyuan Chen, Wensheng Chen, "Thermal Face Recognition based on Physiological Information ", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4675. Accessed: Oct. 22, 2019.
@article{4675-19,
url = {http://sigport.org/4675},
author = {Shinfeng D. Lin; Kuanyuan Chen; Wensheng Chen },
publisher = {IEEE SigPort},
title = {Thermal Face Recognition based on Physiological Information },
year = {2019} }
TY - EJOUR
T1 - Thermal Face Recognition based on Physiological Information
AU - Shinfeng D. Lin; Kuanyuan Chen; Wensheng Chen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4675
ER -
Shinfeng D. Lin, Kuanyuan Chen, Wensheng Chen. (2019). Thermal Face Recognition based on Physiological Information . IEEE SigPort. http://sigport.org/4675
Shinfeng D. Lin, Kuanyuan Chen, Wensheng Chen, 2019. Thermal Face Recognition based on Physiological Information . Available at: http://sigport.org/4675.
Shinfeng D. Lin, Kuanyuan Chen, Wensheng Chen. (2019). "Thermal Face Recognition based on Physiological Information ." Web.
1. Shinfeng D. Lin, Kuanyuan Chen, Wensheng Chen. Thermal Face Recognition based on Physiological Information [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4675

Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES


Computer simulations have facilitated our understanding of the dynamic behavior of the brain and the effect of the medical treatment such as deep brain stimulation. For improving the simulation model, it is essential to develop a method for optimizing parameters of a neuron model from available experimental data. In this paper, we apply Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) to the parameter optimization problem, and compare it with widely used conventional approaches including genetic algorithm (GA) and the Nelder-Mead method.

Paper Details

Authors:
Han Xu, Takahiro Shinozaki, Ryota Kobayashi
Submitted On:
10 May 2019 - 6:02am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster v10.pdf

(27)

Keywords

Subscribe

[1] Han Xu, Takahiro Shinozaki, Ryota Kobayashi, "Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4294. Accessed: Oct. 22, 2019.
@article{4294-19,
url = {http://sigport.org/4294},
author = {Han Xu; Takahiro Shinozaki; Ryota Kobayashi },
publisher = {IEEE SigPort},
title = {Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES},
year = {2019} }
TY - EJOUR
T1 - Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES
AU - Han Xu; Takahiro Shinozaki; Ryota Kobayashi
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4294
ER -
Han Xu, Takahiro Shinozaki, Ryota Kobayashi. (2019). Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES. IEEE SigPort. http://sigport.org/4294
Han Xu, Takahiro Shinozaki, Ryota Kobayashi, 2019. Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES. Available at: http://sigport.org/4294.
Han Xu, Takahiro Shinozaki, Ryota Kobayashi. (2019). "Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES." Web.
1. Han Xu, Takahiro Shinozaki, Ryota Kobayashi. Effective and Stable Neuron Model Optimization Based on Aggregated CMA-ES [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4294

eep Latent Factor Model for Predicting Drug Target Interactions


In drug target interaction (DTI) the interactions of some (a subset) drugs on some (a subset) targets are known. The goal is to predict the interactions of all drugs on all targets. One approach is to formulate this as a matrix completion problem, where the matrix of interactions having drugs along the rows and targets along the columns is partially filled. So far standard matrix completion approaches such as nuclear norm minimization and matrix factorization have been used to address the problem.

Paper Details

Authors:
Aanchal Mongia, Vidit Jain, Emilie Chouzenoux , Angshul Majumdar
Submitted On:
9 May 2019 - 2:50am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

lfm_dti (7).pdf

(36)

Keywords

Subscribe

[1] Aanchal Mongia, Vidit Jain, Emilie Chouzenoux , Angshul Majumdar, "eep Latent Factor Model for Predicting Drug Target Interactions", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4157. Accessed: Oct. 22, 2019.
@article{4157-19,
url = {http://sigport.org/4157},
author = {Aanchal Mongia; Vidit Jain; Emilie Chouzenoux ; Angshul Majumdar },
publisher = {IEEE SigPort},
title = {eep Latent Factor Model for Predicting Drug Target Interactions},
year = {2019} }
TY - EJOUR
T1 - eep Latent Factor Model for Predicting Drug Target Interactions
AU - Aanchal Mongia; Vidit Jain; Emilie Chouzenoux ; Angshul Majumdar
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4157
ER -
Aanchal Mongia, Vidit Jain, Emilie Chouzenoux , Angshul Majumdar. (2019). eep Latent Factor Model for Predicting Drug Target Interactions. IEEE SigPort. http://sigport.org/4157
Aanchal Mongia, Vidit Jain, Emilie Chouzenoux , Angshul Majumdar, 2019. eep Latent Factor Model for Predicting Drug Target Interactions. Available at: http://sigport.org/4157.
Aanchal Mongia, Vidit Jain, Emilie Chouzenoux , Angshul Majumdar. (2019). "eep Latent Factor Model for Predicting Drug Target Interactions." Web.
1. Aanchal Mongia, Vidit Jain, Emilie Chouzenoux , Angshul Majumdar. eep Latent Factor Model for Predicting Drug Target Interactions [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4157

Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies


We propose a modification of linear discriminant analysis, referred to as compressive regularized discriminant analysis (CRDA), for analysis of high-dimensional datasets. CRDA is specially designed for feature elimination purpose and can be used as gene selection method in microarray studies. CRDA lends ideas from ℓq,1 norm minimization algorithms in the multiple measurement vectors (MMV) model and utilizes joint-sparsity promoting hard thresholding for feature elimination.

Paper Details

Authors:
Muhammad Naveed Tabassum and Esa Ollila
Submitted On:
13 April 2018 - 12:03am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

tabassum_crda-hd_poster

(180)

Keywords

Additional Categories

Subscribe

[1] Muhammad Naveed Tabassum and Esa Ollila, "Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2580. Accessed: Oct. 22, 2019.
@article{2580-18,
url = {http://sigport.org/2580},
author = {Muhammad Naveed Tabassum and Esa Ollila },
publisher = {IEEE SigPort},
title = {Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies},
year = {2018} }
TY - EJOUR
T1 - Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies
AU - Muhammad Naveed Tabassum and Esa Ollila
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2580
ER -
Muhammad Naveed Tabassum and Esa Ollila. (2018). Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies. IEEE SigPort. http://sigport.org/2580
Muhammad Naveed Tabassum and Esa Ollila, 2018. Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies. Available at: http://sigport.org/2580.
Muhammad Naveed Tabassum and Esa Ollila. (2018). "Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies." Web.
1. Muhammad Naveed Tabassum and Esa Ollila. Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2580

Face Liveness Detection Using Shearlet Based Feature Descriptors


FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS_Yuming LI

We demonstrate the results of DoG and LBP for comparison purpose. This demo video is available at this link: https://www.youtube.com/watch?v=kUCC0hLSJaU. In addition, in order to show that the proposed method can be directly used in real situation, we completed a real-time implementation of our method and tested it using real data which also include print photo attack, mobile photo attack and video attack. In this demo, 21 frames are analyzed for each detection and the final result is the average score of these 21 frames.

Paper Details

Authors:
Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan
Submitted On:
11 March 2016 - 9:28pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster_FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS_Yuming LI.pdf

(96)

Keywords

Subscribe

[1] Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan, "Face Liveness Detection Using Shearlet Based Feature Descriptors", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/620. Accessed: Oct. 22, 2019.
@article{620-16,
url = {http://sigport.org/620},
author = {Yuming Li; Lai-Man Po; Xuyuan Xu; Litong Feng; Fang Yuan },
publisher = {IEEE SigPort},
title = {Face Liveness Detection Using Shearlet Based Feature Descriptors},
year = {2016} }
TY - EJOUR
T1 - Face Liveness Detection Using Shearlet Based Feature Descriptors
AU - Yuming Li; Lai-Man Po; Xuyuan Xu; Litong Feng; Fang Yuan
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/620
ER -
Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan. (2016). Face Liveness Detection Using Shearlet Based Feature Descriptors. IEEE SigPort. http://sigport.org/620
Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan, 2016. Face Liveness Detection Using Shearlet Based Feature Descriptors. Available at: http://sigport.org/620.
Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan. (2016). "Face Liveness Detection Using Shearlet Based Feature Descriptors." Web.
1. Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan. Face Liveness Detection Using Shearlet Based Feature Descriptors [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/620

FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS

Paper Details

Authors:
Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan
Submitted On:
11 March 2016 - 9:23pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster_FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS_Yuming LI.pdf

(75)

Keywords

Subscribe

[1] Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan, "FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/618. Accessed: Oct. 22, 2019.
@article{618-16,
url = {http://sigport.org/618},
author = {Yuming Li; Lai-Man Po; Xuyuan Xu; Litong Feng; Fang Yuan },
publisher = {IEEE SigPort},
title = {FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS},
year = {2016} }
TY - EJOUR
T1 - FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS
AU - Yuming Li; Lai-Man Po; Xuyuan Xu; Litong Feng; Fang Yuan
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/618
ER -
Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan. (2016). FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS. IEEE SigPort. http://sigport.org/618
Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan, 2016. FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS. Available at: http://sigport.org/618.
Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan. (2016). "FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS." Web.
1. Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan. FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORS [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/618

Models for Spectral Clustering and Their Applications


Microarray Spectral Clustering.

Ph.D. Thesis by Donald McCuan (advisor Andrew Knyazev), Department of Mathematical and Statistical Sciences, University of Colorado Denver, 2012, originally posted at http://math.ucdenver.edu/theses/McCuan_PhdThesis.pdf (881)

Paper Details

Authors:
Donald Donald
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Document Year:
Cite

Document Files

McCuan_PhdThesis.pdf

(881)

Subscribe

[1] Donald Donald, "Models for Spectral Clustering and Their Applications", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/564. Accessed: Oct. 22, 2019.
@article{564-15,
url = {http://sigport.org/564},
author = {Donald Donald },
publisher = {IEEE SigPort},
title = {Models for Spectral Clustering and Their Applications},
year = {2015} }
TY - EJOUR
T1 - Models for Spectral Clustering and Their Applications
AU - Donald Donald
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/564
ER -
Donald Donald. (2015). Models for Spectral Clustering and Their Applications. IEEE SigPort. http://sigport.org/564
Donald Donald, 2015. Models for Spectral Clustering and Their Applications. Available at: http://sigport.org/564.
Donald Donald. (2015). "Models for Spectral Clustering and Their Applications." Web.
1. Donald Donald. Models for Spectral Clustering and Their Applications [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/564

Novel data clustering for microarrays and image segmentation


Spectral Clustering Eigenvalue Problem

We develop novel algorithms and software on parallel computers for data clustering of large datasets. We are interested in applying our approach, e.g., for analysis of large datasets of microarrays or tiling arrays in molecular biology and for segmentation of high resolution images.

Paper Details

Authors:
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Document Year:
Cite

Document Files

camready-1031.ppt

(457)

Subscribe

[1] , "Novel data clustering for microarrays and image segmentation", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/561. Accessed: Oct. 22, 2019.
@article{561-15,
url = {http://sigport.org/561},
author = { },
publisher = {IEEE SigPort},
title = {Novel data clustering for microarrays and image segmentation},
year = {2015} }
TY - EJOUR
T1 - Novel data clustering for microarrays and image segmentation
AU -
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/561
ER -
. (2015). Novel data clustering for microarrays and image segmentation. IEEE SigPort. http://sigport.org/561
, 2015. Novel data clustering for microarrays and image segmentation. Available at: http://sigport.org/561.
. (2015). "Novel data clustering for microarrays and image segmentation." Web.
1. . Novel data clustering for microarrays and image segmentation [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/561

Multiresolution Functional Connectivity Analysis Refines Functional Connectivity Networks in Individual Brains


Recent advances in functional connectivity (FC) analysis of functional magnetic resonance imaging (fMRI) data facilitate the characterization of the brain’s intrinsic functional networks (FC-fMRI). Because the fMRI signal does not provides a perfect representation of neuronal activity, the potential for FC-fMRI to identify functionally relevant networks critically depends upon separating overlapping signals from one another and from external noise. As a step in data preconditioning, researchers often band-pass filter fMRI signals to the range from 0.01 Hz to 0.1 Hz.

Paper Details

Authors:
Alessio Medda, Shella Keilholz
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

JacobBillings_GlobalSIP2015_Presentation_v3.pdf

(454)

Keywords

Subscribe

[1] Alessio Medda, Shella Keilholz, "Multiresolution Functional Connectivity Analysis Refines Functional Connectivity Networks in Individual Brains ", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/493. Accessed: Oct. 22, 2019.
@article{493-15,
url = {http://sigport.org/493},
author = {Alessio Medda; Shella Keilholz },
publisher = {IEEE SigPort},
title = {Multiresolution Functional Connectivity Analysis Refines Functional Connectivity Networks in Individual Brains },
year = {2015} }
TY - EJOUR
T1 - Multiresolution Functional Connectivity Analysis Refines Functional Connectivity Networks in Individual Brains
AU - Alessio Medda; Shella Keilholz
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/493
ER -
Alessio Medda, Shella Keilholz. (2015). Multiresolution Functional Connectivity Analysis Refines Functional Connectivity Networks in Individual Brains . IEEE SigPort. http://sigport.org/493
Alessio Medda, Shella Keilholz, 2015. Multiresolution Functional Connectivity Analysis Refines Functional Connectivity Networks in Individual Brains . Available at: http://sigport.org/493.
Alessio Medda, Shella Keilholz. (2015). "Multiresolution Functional Connectivity Analysis Refines Functional Connectivity Networks in Individual Brains ." Web.
1. Alessio Medda, Shella Keilholz. Multiresolution Functional Connectivity Analysis Refines Functional Connectivity Networks in Individual Brains [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/493

Pages