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

Image, Video, and Multidimensional Signal Processing

MULTI-THRESHOLD LIP CONTOUR DETECTION

Panagiota Spyridonos

In this work, we propose a novel, multi-threshold method for lip contour extraction from high-resolution static lip images acquired in an uncontrolled environment and emphasizing on the contour details.
The introduced method is a “Divide and conquer” approach. We broke the problem of lip contour extraction into two base sub-problems of locating the upper and lower lip contours using a novel threshold selection algorithm and combining them into the solution for the original lip contour.

Paper Details

Authors:
Panagiota Spyridonos
Panagiota Spyridonos, Aggelos Fares Saint, Aristidis Likas, Georgios Gaitanis, Ioannis Bassukas
Submitted On:
4 October 2018 - 10:59am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP 2018

(85)

Keywords

Additional Categories

Subscribe

Send Author a Private Message
[1] Panagiota Spyridonos, Aggelos Fares Saint, Aristidis Likas, Georgios Gaitanis, Ioannis Bassukas, "MULTI-THRESHOLD LIP CONTOUR DETECTION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3428. Accessed: Sep. 23, 2020.
@article{3428-18,
url = {http://sigport.org/3428},
author = {Panagiota Spyridonos; Aggelos Fares Saint; Aristidis Likas; Georgios Gaitanis; Ioannis Bassukas },
publisher = {IEEE SigPort},
title = {MULTI-THRESHOLD LIP CONTOUR DETECTION},
year = {2018} }
TY - EJOUR
T1 - MULTI-THRESHOLD LIP CONTOUR DETECTION
AU - Panagiota Spyridonos; Aggelos Fares Saint; Aristidis Likas; Georgios Gaitanis; Ioannis Bassukas
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3428
ER -
Panagiota Spyridonos, Aggelos Fares Saint, Aristidis Likas, Georgios Gaitanis, Ioannis Bassukas. (2018). MULTI-THRESHOLD LIP CONTOUR DETECTION. IEEE SigPort. http://sigport.org/3428
Panagiota Spyridonos, Aggelos Fares Saint, Aristidis Likas, Georgios Gaitanis, Ioannis Bassukas, 2018. MULTI-THRESHOLD LIP CONTOUR DETECTION. Available at: http://sigport.org/3428.
Panagiota Spyridonos, Aggelos Fares Saint, Aristidis Likas, Georgios Gaitanis, Ioannis Bassukas. (2018). "MULTI-THRESHOLD LIP CONTOUR DETECTION." Web.
1. Panagiota Spyridonos, Aggelos Fares Saint, Aristidis Likas, Georgios Gaitanis, Ioannis Bassukas. MULTI-THRESHOLD LIP CONTOUR DETECTION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3428

Near-Constant Time Bilateral Filter for High-Dimensional Images

Christina Karam
Kenjiro Sugimoto

Paper Details

Authors:
Christina Karam
Kenjiro Sugimoto
Keigo Hirakawa
Submitted On:
4 October 2018 - 10:55am
Short Link:
Type:

Document Files

Poster_Karam

(112)

Keywords

Subscribe

Send Author a Private Message
[1] Keigo Hirakawa, "Near-Constant Time Bilateral Filter for High-Dimensional Images", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3427. Accessed: Sep. 23, 2020.
@article{3427-18,
url = {http://sigport.org/3427},
author = {Keigo Hirakawa },
publisher = {IEEE SigPort},
title = {Near-Constant Time Bilateral Filter for High-Dimensional Images},
year = {2018} }
TY - EJOUR
T1 - Near-Constant Time Bilateral Filter for High-Dimensional Images
AU - Keigo Hirakawa
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3427
ER -
Keigo Hirakawa. (2018). Near-Constant Time Bilateral Filter for High-Dimensional Images. IEEE SigPort. http://sigport.org/3427
Keigo Hirakawa, 2018. Near-Constant Time Bilateral Filter for High-Dimensional Images. Available at: http://sigport.org/3427.
Keigo Hirakawa. (2018). "Near-Constant Time Bilateral Filter for High-Dimensional Images." Web.
1. Keigo Hirakawa. Near-Constant Time Bilateral Filter for High-Dimensional Images [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3427

A 2.5D APPROACH to 360 PANORAMA VIDEO STABILIZATION

Yung-Yu Chuang

This paper presents a method for stabilizing both cylindrical and spherical panorama videos with a 360-degree field of view. We observe that rotation needs to be extremely smooth for 360 videos to maintain global motion coherency and avoid wobbling. Our method decouples the rotation from other motions and applies different strategies for smoothing them. The proposed approach is 2.5D as it estimates 3D rotations without involving 3D structure-from-motion methods. Therefore, it is more robust and can be performed in an incremental way.

Paper Details

Authors:
Yung-Yu Chuang
Lin-Chen Shen, Tzu-Kuei Huang, Chu-Song Chen, Yung-Yu Chuang
Submitted On:
4 October 2018 - 9:31am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip2018_stabilization_poster.pdf

(117)

Keywords

Subscribe

Send Author a Private Message
[1] Lin-Chen Shen, Tzu-Kuei Huang, Chu-Song Chen, Yung-Yu Chuang, "A 2.5D APPROACH to 360 PANORAMA VIDEO STABILIZATION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3407. Accessed: Sep. 23, 2020.
@article{3407-18,
url = {http://sigport.org/3407},
author = {Lin-Chen Shen; Tzu-Kuei Huang; Chu-Song Chen; Yung-Yu Chuang },
publisher = {IEEE SigPort},
title = {A 2.5D APPROACH to 360 PANORAMA VIDEO STABILIZATION},
year = {2018} }
TY - EJOUR
T1 - A 2.5D APPROACH to 360 PANORAMA VIDEO STABILIZATION
AU - Lin-Chen Shen; Tzu-Kuei Huang; Chu-Song Chen; Yung-Yu Chuang
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3407
ER -
Lin-Chen Shen, Tzu-Kuei Huang, Chu-Song Chen, Yung-Yu Chuang. (2018). A 2.5D APPROACH to 360 PANORAMA VIDEO STABILIZATION. IEEE SigPort. http://sigport.org/3407
Lin-Chen Shen, Tzu-Kuei Huang, Chu-Song Chen, Yung-Yu Chuang, 2018. A 2.5D APPROACH to 360 PANORAMA VIDEO STABILIZATION. Available at: http://sigport.org/3407.
Lin-Chen Shen, Tzu-Kuei Huang, Chu-Song Chen, Yung-Yu Chuang. (2018). "A 2.5D APPROACH to 360 PANORAMA VIDEO STABILIZATION." Web.
1. Lin-Chen Shen, Tzu-Kuei Huang, Chu-Song Chen, Yung-Yu Chuang. A 2.5D APPROACH to 360 PANORAMA VIDEO STABILIZATION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3407

GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION

Yung-Yu Chuang

This paper proposes a swung-to-cylinder projection model for mapping a sphere to a plane. It can be used to create a semi-perspective image from a panoramic image. The model has two steps. In the first step, the sphere is projected onto a swung surface constructed by a circular profile and a rounded rectangular trajectory. In the second step, the projected image on the swung surface is mapped onto a cylinder through the perspective projection. We also propose methods for automatically determining proper parameters for the projection model based on image content.

Paper Details

Authors:
Yung-Yu Chuang
Che-Han Chang, Wei-Sheng Lai, Yung-Yu Chuang
Submitted On:
4 October 2018 - 9:28am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip2018_swung_poster.pdf

(122)

Keywords

Subscribe

Send Author a Private Message
[1] Che-Han Chang, Wei-Sheng Lai, Yung-Yu Chuang, "GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3403. Accessed: Sep. 23, 2020.
@article{3403-18,
url = {http://sigport.org/3403},
author = {Che-Han Chang; Wei-Sheng Lai; Yung-Yu Chuang },
publisher = {IEEE SigPort},
title = {GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION},
year = {2018} }
TY - EJOUR
T1 - GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION
AU - Che-Han Chang; Wei-Sheng Lai; Yung-Yu Chuang
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3403
ER -
Che-Han Chang, Wei-Sheng Lai, Yung-Yu Chuang. (2018). GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION. IEEE SigPort. http://sigport.org/3403
Che-Han Chang, Wei-Sheng Lai, Yung-Yu Chuang, 2018. GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION. Available at: http://sigport.org/3403.
Che-Han Chang, Wei-Sheng Lai, Yung-Yu Chuang. (2018). "GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION." Web.
1. Che-Han Chang, Wei-Sheng Lai, Yung-Yu Chuang. GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3403

Estimation of the regularization parameter of an on-line NMF with minimum volume constraint

Ludivine NUS

Paper Details

Authors:
Ludivine NUS
Sebastian MIRON, David BRIE
Submitted On:
6 July 2018 - 8:46am
Short Link:
Type:
Event:

Document Files

NUS_SAM2018.pdf

(181)

Keywords

Subscribe

Send Author a Private Message
[1] Sebastian MIRON, David BRIE, "Estimation of the regularization parameter of an on-line NMF with minimum volume constraint", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3368. Accessed: Sep. 23, 2020.
@article{3368-18,
url = {http://sigport.org/3368},
author = {Sebastian MIRON; David BRIE },
publisher = {IEEE SigPort},
title = {Estimation of the regularization parameter of an on-line NMF with minimum volume constraint},
year = {2018} }
TY - EJOUR
T1 - Estimation of the regularization parameter of an on-line NMF with minimum volume constraint
AU - Sebastian MIRON; David BRIE
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3368
ER -
Sebastian MIRON, David BRIE. (2018). Estimation of the regularization parameter of an on-line NMF with minimum volume constraint. IEEE SigPort. http://sigport.org/3368
Sebastian MIRON, David BRIE, 2018. Estimation of the regularization parameter of an on-line NMF with minimum volume constraint. Available at: http://sigport.org/3368.
Sebastian MIRON, David BRIE. (2018). "Estimation of the regularization parameter of an on-line NMF with minimum volume constraint." Web.
1. Sebastian MIRON, David BRIE. Estimation of the regularization parameter of an on-line NMF with minimum volume constraint [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3368

RCDFNN: Robust Change Detection based on Convolutional Fusion Neural Network

Chunlei Cai

Video change detection, which plays an important role in computer vision, is far from being well resolved due to the complexity of diverse scenes in real world. Most of the current methods are designed based on hand-crafted features and perform well in some certain scenes but may fail on others. This paper puts up forward a deep learning based method to automatically fuse multiple basic detections into an optimal

Paper Details

Authors:
Chunlei Cai
Submitted On:
20 April 2018 - 10:43am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_poster.pdf

(274)

Keywords

Subscribe

Send Author a Private Message
[1] , " RCDFNN: Robust Change Detection based on Convolutional Fusion Neural Network", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3107. Accessed: Sep. 23, 2020.
@article{3107-18,
url = {http://sigport.org/3107},
author = { },
publisher = {IEEE SigPort},
title = { RCDFNN: Robust Change Detection based on Convolutional Fusion Neural Network},
year = {2018} }
TY - EJOUR
T1 - RCDFNN: Robust Change Detection based on Convolutional Fusion Neural Network
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3107
ER -
. (2018). RCDFNN: Robust Change Detection based on Convolutional Fusion Neural Network. IEEE SigPort. http://sigport.org/3107
, 2018. RCDFNN: Robust Change Detection based on Convolutional Fusion Neural Network. Available at: http://sigport.org/3107.
. (2018). " RCDFNN: Robust Change Detection based on Convolutional Fusion Neural Network." Web.
1. . RCDFNN: Robust Change Detection based on Convolutional Fusion Neural Network [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3107

Deep Blind Image Quality Assessment by Learning Sensitivity Map

Sanghoon Lee

Applying a deep convolutional neural network CNN to no reference image quality assessment (NR-IQA) is a challenging task due to the lack of a training database. In this paper, we propose a CNN-based NR-IQA framework that can effectively solve this problem. The proposed method–the Deep Blind image Quality Assessment predictor (DeepBQA)– adopts two-step training stages to avoid overfitting. In the first stage, a ground-truth objective error map is generated and used as a proxy training target.

Paper Details

Authors:
Sanghoon Lee
Submitted On:
20 April 2018 - 1:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_Sanghoon_Lee.pdf

(342)

Keywords

Subscribe

Send Author a Private Message
[1] , "Deep Blind Image Quality Assessment by Learning Sensitivity Map", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3074. Accessed: Sep. 23, 2020.
@article{3074-18,
url = {http://sigport.org/3074},
author = { },
publisher = {IEEE SigPort},
title = {Deep Blind Image Quality Assessment by Learning Sensitivity Map},
year = {2018} }
TY - EJOUR
T1 - Deep Blind Image Quality Assessment by Learning Sensitivity Map
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3074
ER -
. (2018). Deep Blind Image Quality Assessment by Learning Sensitivity Map. IEEE SigPort. http://sigport.org/3074
, 2018. Deep Blind Image Quality Assessment by Learning Sensitivity Map. Available at: http://sigport.org/3074.
. (2018). "Deep Blind Image Quality Assessment by Learning Sensitivity Map." Web.
1. . Deep Blind Image Quality Assessment by Learning Sensitivity Map [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3074

BAYESIAN GENERATIVE MODEL BASED ON COLOR HISTOGRAM OF ORIENTED PHASE AND HISTOGRAM OF ORIENTED OPTICAL FLOW FOR RARE EVENT DETECTION IN CROWDED SCENES

Dieudonne ATREVI

Paper Details

Authors:
Dieudonne ATREVI
D. Fabrice ATREVI, Damien VIVET, Bruno EMILE
Submitted On:
20 April 2018 - 1:06am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_Icassp_ATREVI.pdf

(256)

Keywords

Subscribe

Send Author a Private Message
[1] D. Fabrice ATREVI, Damien VIVET, Bruno EMILE, "BAYESIAN GENERATIVE MODEL BASED ON COLOR HISTOGRAM OF ORIENTED PHASE AND HISTOGRAM OF ORIENTED OPTICAL FLOW FOR RARE EVENT DETECTION IN CROWDED SCENES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3071. Accessed: Sep. 23, 2020.
@article{3071-18,
url = {http://sigport.org/3071},
author = { D. Fabrice ATREVI; Damien VIVET; Bruno EMILE },
publisher = {IEEE SigPort},
title = {BAYESIAN GENERATIVE MODEL BASED ON COLOR HISTOGRAM OF ORIENTED PHASE AND HISTOGRAM OF ORIENTED OPTICAL FLOW FOR RARE EVENT DETECTION IN CROWDED SCENES},
year = {2018} }
TY - EJOUR
T1 - BAYESIAN GENERATIVE MODEL BASED ON COLOR HISTOGRAM OF ORIENTED PHASE AND HISTOGRAM OF ORIENTED OPTICAL FLOW FOR RARE EVENT DETECTION IN CROWDED SCENES
AU - D. Fabrice ATREVI; Damien VIVET; Bruno EMILE
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3071
ER -
D. Fabrice ATREVI, Damien VIVET, Bruno EMILE. (2018). BAYESIAN GENERATIVE MODEL BASED ON COLOR HISTOGRAM OF ORIENTED PHASE AND HISTOGRAM OF ORIENTED OPTICAL FLOW FOR RARE EVENT DETECTION IN CROWDED SCENES. IEEE SigPort. http://sigport.org/3071
D. Fabrice ATREVI, Damien VIVET, Bruno EMILE, 2018. BAYESIAN GENERATIVE MODEL BASED ON COLOR HISTOGRAM OF ORIENTED PHASE AND HISTOGRAM OF ORIENTED OPTICAL FLOW FOR RARE EVENT DETECTION IN CROWDED SCENES. Available at: http://sigport.org/3071.
D. Fabrice ATREVI, Damien VIVET, Bruno EMILE. (2018). "BAYESIAN GENERATIVE MODEL BASED ON COLOR HISTOGRAM OF ORIENTED PHASE AND HISTOGRAM OF ORIENTED OPTICAL FLOW FOR RARE EVENT DETECTION IN CROWDED SCENES." Web.
1. D. Fabrice ATREVI, Damien VIVET, Bruno EMILE. BAYESIAN GENERATIVE MODEL BASED ON COLOR HISTOGRAM OF ORIENTED PHASE AND HISTOGRAM OF ORIENTED OPTICAL FLOW FOR RARE EVENT DETECTION IN CROWDED SCENES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3071

Analysis and Optimization of Aperture Design in Computational Imaging

Adam Yedidia

There is growing interest in the use of coded aperture imaging systems for a variety of applications. Using an analysis framework based on mutual information, we examine the fundamental limits of such systems—and the associated optimum aperture coding—under simple but meaningful propagation and sensor models. Among other results, we show that when SNR is high and thermal noise dominates shot noise, spectrally-flat masks, which have 50% transmissivity, are optimal, but that when shot noise dominates thermal noise, randomly generated masks with lower transmissivity offer greater performance.

Paper Details

Authors:
Adam Yedidia
Adam Yedidia, Christos Thrampoulidis, Gregory Wornell
Submitted On:
19 April 2018 - 9:20pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_talk_short.pptx

(191)

Keywords

Subscribe

Send Author a Private Message
[1] Adam Yedidia, Christos Thrampoulidis, Gregory Wornell, "Analysis and Optimization of Aperture Design in Computational Imaging", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3049. Accessed: Sep. 23, 2020.
@article{3049-18,
url = {http://sigport.org/3049},
author = {Adam Yedidia; Christos Thrampoulidis; Gregory Wornell },
publisher = {IEEE SigPort},
title = {Analysis and Optimization of Aperture Design in Computational Imaging},
year = {2018} }
TY - EJOUR
T1 - Analysis and Optimization of Aperture Design in Computational Imaging
AU - Adam Yedidia; Christos Thrampoulidis; Gregory Wornell
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3049
ER -
Adam Yedidia, Christos Thrampoulidis, Gregory Wornell. (2018). Analysis and Optimization of Aperture Design in Computational Imaging. IEEE SigPort. http://sigport.org/3049
Adam Yedidia, Christos Thrampoulidis, Gregory Wornell, 2018. Analysis and Optimization of Aperture Design in Computational Imaging. Available at: http://sigport.org/3049.
Adam Yedidia, Christos Thrampoulidis, Gregory Wornell. (2018). "Analysis and Optimization of Aperture Design in Computational Imaging." Web.
1. Adam Yedidia, Christos Thrampoulidis, Gregory Wornell. Analysis and Optimization of Aperture Design in Computational Imaging [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3049

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

Xiao Yang

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

Paper Details

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

Document Files

xiao_yang.pdf

(234)

Keywords

Subscribe

Send Author a Private Message
[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: Sep. 23, 2020.
@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

Pages