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

Image, Video, and Multidimensional Signal Processing

RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES


Cross-modal sketch-photo recognition is of vital importance
in law enforcement and public security. Most existing methods
are dedicated to bridging the gap between the low-level
visual features of sketches and photo images, which is limited
due to intrinsic differences in pixel values. In this paper, based
on the intuition that sketches and photo images are highly correlated
in the semantic domain, we propose to jointly utilize
the low-level visual features and high-level facial attributes to

xiao_yang.pdf

PDF icon xiao_yang.pdf (100 downloads)

Paper Details

Authors:
Submitted On:
19 April 2018 - 2:49pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

xiao_yang.pdf

(100 downloads)

Subscribe

[1] , "RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3001. Accessed: Nov. 13, 2018.
@article{3001-18,
url = {http://sigport.org/3001},
author = { },
publisher = {IEEE SigPort},
title = {RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES},
year = {2018} }
TY - EJOUR
T1 - RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3001
ER -
. (2018). RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES. IEEE SigPort. http://sigport.org/3001
, 2018. RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES. Available at: http://sigport.org/3001.
. (2018). "RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES." Web.
1. . RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3001

RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES


Cross-modal sketch-photo recognition is of vital importance
in law enforcement and public security. Most existing methods
are dedicated to bridging the gap between the low-level
visual features of sketches and photo images, which is limited
due to intrinsic differences in pixel values. In this paper, based
on the intuition that sketches and photo images are highly correlated
in the semantic domain, we propose to jointly utilize
the low-level visual features and high-level facial attributes to

xiao_yang.pdf

PDF icon xiao_yang.pdf (102 downloads)

Paper Details

Authors:
Submitted On:
19 April 2018 - 2:49pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

xiao_yang.pdf

(102 downloads)

Subscribe

[1] , "RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3000. Accessed: Nov. 13, 2018.
@article{3000-18,
url = {http://sigport.org/3000},
author = { },
publisher = {IEEE SigPort},
title = {RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES},
year = {2018} }
TY - EJOUR
T1 - RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3000
ER -
. (2018). RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES. IEEE SigPort. http://sigport.org/3000
, 2018. RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES. Available at: http://sigport.org/3000.
. (2018). "RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES." Web.
1. . RECOGNIZING MINIMAL FACIAL SKETCH BY GENERATING PHOTOREALISTIC FACES WITH THE GUIDANCE OF DESCRIPTIVE ATTRIBUTES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3000

Image Restoration with Deep Generative Models


Many image restoration problems are ill-posed in nature, hence, beyond the input image, most existing methods rely on a carefully engineered image prior, which enforces some local image consistency in the recovered image. How tightly the prior assumptions are fulfilled has a big impact on the resulting task performance. To obtain more flexibility, in this work, we proposed to design the image prior in a data-driven manner. Instead of explicitly defining the prior, we learn it using deep generative models.

Paper Details

Authors:
Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do
Submitted On:
17 April 2018 - 12:40am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

presentation.pdf

(372 downloads)

Subscribe

[1] Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do, "Image Restoration with Deep Generative Models", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2927. Accessed: Nov. 13, 2018.
@article{2927-18,
url = {http://sigport.org/2927},
author = {Chen Chen; Alexander G. Schwing; Mark Hasegawa-Johnson; Minh N. Do },
publisher = {IEEE SigPort},
title = {Image Restoration with Deep Generative Models},
year = {2018} }
TY - EJOUR
T1 - Image Restoration with Deep Generative Models
AU - Chen Chen; Alexander G. Schwing; Mark Hasegawa-Johnson; Minh N. Do
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2927
ER -
Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do. (2018). Image Restoration with Deep Generative Models. IEEE SigPort. http://sigport.org/2927
Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do, 2018. Image Restoration with Deep Generative Models. Available at: http://sigport.org/2927.
Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do. (2018). "Image Restoration with Deep Generative Models." Web.
1. Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do. Image Restoration with Deep Generative Models [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2927

SEQUENTIAL ADAPTIVE DETECTION FOR IN-SITU TRANSMISSION ELECTRON MICROSCOPY (TEM)


We develop new efficient online algorithms for detecting transient sparse signals in TEM video sequences, by adopting the recently developed framework for sequential detection jointly with online convex optimization [1]. We cast the problem as detecting an unknown sparse mean shift of Gaussian observations, and develop adaptive CUSUM and adaptive SSRS procedures, which are based on likelihood ratio statistics with post-change mean vector being online maximum likelihood estimators with ℓ1. We demonstrate the meritorious performance of our algorithms for TEM imaging using real data.

icassp2018_poster.pdf

PDF icon poster (205 downloads)

Paper Details

Authors:
Yang Cao, Shixiang Zhu, Yao Xie, Jordan Key, Josh Kacher, Raymond Unocic, Christopher Rouleau
Submitted On:
13 April 2018 - 11:40pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster

(205 downloads)

Subscribe

[1] Yang Cao, Shixiang Zhu, Yao Xie, Jordan Key, Josh Kacher, Raymond Unocic, Christopher Rouleau, "SEQUENTIAL ADAPTIVE DETECTION FOR IN-SITU TRANSMISSION ELECTRON MICROSCOPY (TEM)", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2789. Accessed: Nov. 13, 2018.
@article{2789-18,
url = {http://sigport.org/2789},
author = {Yang Cao; Shixiang Zhu; Yao Xie; Jordan Key; Josh Kacher; Raymond Unocic; Christopher Rouleau },
publisher = {IEEE SigPort},
title = {SEQUENTIAL ADAPTIVE DETECTION FOR IN-SITU TRANSMISSION ELECTRON MICROSCOPY (TEM)},
year = {2018} }
TY - EJOUR
T1 - SEQUENTIAL ADAPTIVE DETECTION FOR IN-SITU TRANSMISSION ELECTRON MICROSCOPY (TEM)
AU - Yang Cao; Shixiang Zhu; Yao Xie; Jordan Key; Josh Kacher; Raymond Unocic; Christopher Rouleau
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2789
ER -
Yang Cao, Shixiang Zhu, Yao Xie, Jordan Key, Josh Kacher, Raymond Unocic, Christopher Rouleau. (2018). SEQUENTIAL ADAPTIVE DETECTION FOR IN-SITU TRANSMISSION ELECTRON MICROSCOPY (TEM). IEEE SigPort. http://sigport.org/2789
Yang Cao, Shixiang Zhu, Yao Xie, Jordan Key, Josh Kacher, Raymond Unocic, Christopher Rouleau, 2018. SEQUENTIAL ADAPTIVE DETECTION FOR IN-SITU TRANSMISSION ELECTRON MICROSCOPY (TEM). Available at: http://sigport.org/2789.
Yang Cao, Shixiang Zhu, Yao Xie, Jordan Key, Josh Kacher, Raymond Unocic, Christopher Rouleau. (2018). "SEQUENTIAL ADAPTIVE DETECTION FOR IN-SITU TRANSMISSION ELECTRON MICROSCOPY (TEM)." Web.
1. Yang Cao, Shixiang Zhu, Yao Xie, Jordan Key, Josh Kacher, Raymond Unocic, Christopher Rouleau. SEQUENTIAL ADAPTIVE DETECTION FOR IN-SITU TRANSMISSION ELECTRON MICROSCOPY (TEM) [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2789

LOW RESOLUTION FACE RECOGNITION AND RECONSTRUCTION VIA DEEP CANONICAL CORRELATION ANALYSIS


Low-resolution (LR) face identification is always a challenge in computer vision. In this paper, we propose a new LR face recognition and reconstruction method using deep canonical correlation analysis (DCCA). Unlike linear CCA-based methods, our proposed method can learn flexible nonlinear representations by passing LR and high-resolution (HR) image principal component features through multiple stacked layers of nonlinear transformation.

Paper Details

Authors:
Zhao Zhang, Yun-Hao Yuan, Xiao-Bo Shen, Yun Li
Submitted On:
13 April 2018 - 11:47am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2018-poster-wide.pdf

(165 downloads)

Subscribe

[1] Zhao Zhang, Yun-Hao Yuan, Xiao-Bo Shen, Yun Li, "LOW RESOLUTION FACE RECOGNITION AND RECONSTRUCTION VIA DEEP CANONICAL CORRELATION ANALYSIS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2722. Accessed: Nov. 13, 2018.
@article{2722-18,
url = {http://sigport.org/2722},
author = {Zhao Zhang; Yun-Hao Yuan; Xiao-Bo Shen; Yun Li },
publisher = {IEEE SigPort},
title = {LOW RESOLUTION FACE RECOGNITION AND RECONSTRUCTION VIA DEEP CANONICAL CORRELATION ANALYSIS},
year = {2018} }
TY - EJOUR
T1 - LOW RESOLUTION FACE RECOGNITION AND RECONSTRUCTION VIA DEEP CANONICAL CORRELATION ANALYSIS
AU - Zhao Zhang; Yun-Hao Yuan; Xiao-Bo Shen; Yun Li
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2722
ER -
Zhao Zhang, Yun-Hao Yuan, Xiao-Bo Shen, Yun Li. (2018). LOW RESOLUTION FACE RECOGNITION AND RECONSTRUCTION VIA DEEP CANONICAL CORRELATION ANALYSIS. IEEE SigPort. http://sigport.org/2722
Zhao Zhang, Yun-Hao Yuan, Xiao-Bo Shen, Yun Li, 2018. LOW RESOLUTION FACE RECOGNITION AND RECONSTRUCTION VIA DEEP CANONICAL CORRELATION ANALYSIS. Available at: http://sigport.org/2722.
Zhao Zhang, Yun-Hao Yuan, Xiao-Bo Shen, Yun Li. (2018). "LOW RESOLUTION FACE RECOGNITION AND RECONSTRUCTION VIA DEEP CANONICAL CORRELATION ANALYSIS." Web.
1. Zhao Zhang, Yun-Hao Yuan, Xiao-Bo Shen, Yun Li. LOW RESOLUTION FACE RECOGNITION AND RECONSTRUCTION VIA DEEP CANONICAL CORRELATION ANALYSIS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2722

Block-coordinate proximal algorithms for scale-free texture segmentation


Texture segmentation still constitutes an on-going challenge, especially when processing large-size images.
Recently, procedures integrating a scale-free (or fractal)wavelet-leader model allowed the problem to be reformulated in a convex optimization framework by including a TV penalization. In this case, the TV penalty plays

Paper Details

Authors:
Barbara Pascal, Nelly Pustelnik, Patrice Abry, Jean-Christophe Pesquet
Submitted On:
18 April 2018 - 12:00am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2018.pdf

(82 downloads)

Subscribe

[1] Barbara Pascal, Nelly Pustelnik, Patrice Abry, Jean-Christophe Pesquet, "Block-coordinate proximal algorithms for scale-free texture segmentation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2716. Accessed: Nov. 13, 2018.
@article{2716-18,
url = {http://sigport.org/2716},
author = {Barbara Pascal; Nelly Pustelnik; Patrice Abry; Jean-Christophe Pesquet },
publisher = {IEEE SigPort},
title = {Block-coordinate proximal algorithms for scale-free texture segmentation},
year = {2018} }
TY - EJOUR
T1 - Block-coordinate proximal algorithms for scale-free texture segmentation
AU - Barbara Pascal; Nelly Pustelnik; Patrice Abry; Jean-Christophe Pesquet
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2716
ER -
Barbara Pascal, Nelly Pustelnik, Patrice Abry, Jean-Christophe Pesquet. (2018). Block-coordinate proximal algorithms for scale-free texture segmentation. IEEE SigPort. http://sigport.org/2716
Barbara Pascal, Nelly Pustelnik, Patrice Abry, Jean-Christophe Pesquet, 2018. Block-coordinate proximal algorithms for scale-free texture segmentation. Available at: http://sigport.org/2716.
Barbara Pascal, Nelly Pustelnik, Patrice Abry, Jean-Christophe Pesquet. (2018). "Block-coordinate proximal algorithms for scale-free texture segmentation." Web.
1. Barbara Pascal, Nelly Pustelnik, Patrice Abry, Jean-Christophe Pesquet. Block-coordinate proximal algorithms for scale-free texture segmentation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2716

Unsupervised Image Segmentation by Backpropagation


We investigate the use of convolutional neural networks (CNNs) for unsupervised image segmentation. As in the case of supervised image segmentation, the proposed CNN assigns labels to pixels that denote the cluster to which the pixel belongs. In the unsupervised scenario, however, no training images or ground truth labels of pixels are given beforehand. Therefore, once when a target image is input, we jointly optimize the pixel labels together with feature representations while their parameters are updated by gradient descent.

Paper Details

Authors:
Submitted On:
13 April 2018 - 10:20am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_kanezaki_outline.pdf

(172 downloads)

Subscribe

[1] , "Unsupervised Image Segmentation by Backpropagation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2710. Accessed: Nov. 13, 2018.
@article{2710-18,
url = {http://sigport.org/2710},
author = { },
publisher = {IEEE SigPort},
title = {Unsupervised Image Segmentation by Backpropagation},
year = {2018} }
TY - EJOUR
T1 - Unsupervised Image Segmentation by Backpropagation
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2710
ER -
. (2018). Unsupervised Image Segmentation by Backpropagation. IEEE SigPort. http://sigport.org/2710
, 2018. Unsupervised Image Segmentation by Backpropagation. Available at: http://sigport.org/2710.
. (2018). "Unsupervised Image Segmentation by Backpropagation." Web.
1. . Unsupervised Image Segmentation by Backpropagation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2710

SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION


Unsupervised cross-database facial expression recognition(FER) is a challenging problem, in which the training and testing samples belong to different facial expression databases. For this reason, the training (source) and testing (target) facial expression samples would have different feature distributions and hence the performance of lots of existing FER methods may decrease.

Paper Details

Authors:
Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu
Submitted On:
13 April 2018 - 8:17am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_2838.pdf

(82 downloads)

Subscribe

[1] Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu, "SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2696. Accessed: Nov. 13, 2018.
@article{2696-18,
url = {http://sigport.org/2696},
author = {Baofeng Zhang; Yuan Zong; Li Liu;Jie Chen; Guoying Zhao; Junchao Zhu },
publisher = {IEEE SigPort},
title = {SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION},
year = {2018} }
TY - EJOUR
T1 - SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION
AU - Baofeng Zhang; Yuan Zong; Li Liu;Jie Chen; Guoying Zhao; Junchao Zhu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2696
ER -
Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu. (2018). SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION. IEEE SigPort. http://sigport.org/2696
Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu, 2018. SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION. Available at: http://sigport.org/2696.
Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu. (2018). "SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION." Web.
1. Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu. SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2696

IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN


Matrix factorization (MF) and its extensions have been intensively studied in computer vision and machine learning. In this paper, unsupervised and supervised learning methods based on MF technique on complex domain are introduced. Projective complex matrix factorization (PCMF) and discriminant projective complex matrix factorization (DPCMF) present two frameworks of projecting complex data to a lower dimension space. The optimization problems are formulated as the minimization of the real-valued functions of complex variables.

Paper Details

Authors:
Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang
Submitted On:
13 April 2018 - 2:14am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_DPCMF_2.pdf

(122 downloads)

Subscribe

[1] Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang, "IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2620. Accessed: Nov. 13, 2018.
@article{2620-18,
url = {http://sigport.org/2620},
author = {Manh-Quan Bui; Viet-Hang Duong; Yung-Hui Li; Tzu-Chiang Tai; Jia-Ching Wang },
publisher = {IEEE SigPort},
title = {IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN},
year = {2018} }
TY - EJOUR
T1 - IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN
AU - Manh-Quan Bui; Viet-Hang Duong; Yung-Hui Li; Tzu-Chiang Tai; Jia-Ching Wang
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2620
ER -
Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang. (2018). IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN. IEEE SigPort. http://sigport.org/2620
Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang, 2018. IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN. Available at: http://sigport.org/2620.
Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang. (2018). "IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN." Web.
1. Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang. IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2620

IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN


Matrix factorization (MF) and its extensions have been intensively studied in computer vision and machine learning. In this paper, unsupervised and supervised learning methods based on MF technique on complex domain are introduced. Projective complex matrix factorization (PCMF) and discriminant projective complex matrix factorization (DPCMF) present two frameworks of projecting complex data to a lower dimension space. The optimization problems are formulated as the minimization of the real-valued functions of complex variables.

Paper Details

Authors:
Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang
Submitted On:
13 April 2018 - 2:14am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_DPCMF_2.pdf

(122 downloads)

Subscribe

[1] Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang, "IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2619. Accessed: Nov. 13, 2018.
@article{2619-18,
url = {http://sigport.org/2619},
author = {Manh-Quan Bui; Viet-Hang Duong; Yung-Hui Li; Tzu-Chiang Tai; Jia-Ching Wang },
publisher = {IEEE SigPort},
title = {IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN},
year = {2018} }
TY - EJOUR
T1 - IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN
AU - Manh-Quan Bui; Viet-Hang Duong; Yung-Hui Li; Tzu-Chiang Tai; Jia-Ching Wang
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2619
ER -
Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang. (2018). IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN. IEEE SigPort. http://sigport.org/2619
Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang, 2018. IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN. Available at: http://sigport.org/2619.
Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang. (2018). "IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN." Web.
1. Manh-Quan Bui, Viet-Hang Duong, Yung-Hui Li, Tzu-Chiang Tai, Jia-Ching Wang. IMAGE REPRESENTATION USING SUPERVISED AND UNSUPERVISED LEARNING METHODS ON COMPLEX DOMAIN [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2619

Pages