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

Image/Video Processing

CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING


A simple and scalable denoising algorithm is proposed that can be applied to a wide range of source and noise models. At the core of the proposed CUDE algorithm is symbol-by-symbol universal denoising used by the celebrated DUDE algorithm, whereby the optimal estimate of the source from an unknown distribution is computed by inverting the empirical distribution of the noisy observation sequence by a deep neural network, which naturally and implicitly aggregates multiple contexts of similar characteristics and estimates the conditional distribution more accurately.

Paper Details

Authors:
Jongha Jon Ryu, Young-Han Kim
Submitted On:
8 October 2018 - 3:38am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip2018-poster-cude.pdf

(54)

Subscribe

[1] Jongha Jon Ryu, Young-Han Kim, "CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3616. Accessed: Apr. 25, 2019.
@article{3616-18,
url = {http://sigport.org/3616},
author = {Jongha Jon Ryu; Young-Han Kim },
publisher = {IEEE SigPort},
title = {CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING},
year = {2018} }
TY - EJOUR
T1 - CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING
AU - Jongha Jon Ryu; Young-Han Kim
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3616
ER -
Jongha Jon Ryu, Young-Han Kim. (2018). CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING. IEEE SigPort. http://sigport.org/3616
Jongha Jon Ryu, Young-Han Kim, 2018. CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING. Available at: http://sigport.org/3616.
Jongha Jon Ryu, Young-Han Kim. (2018). "CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING." Web.
1. Jongha Jon Ryu, Young-Han Kim. CONDITIONAL DISTRIBUTION LEARNING WITH NEURAL NETWORKS AND ITS APPLICATION TO UNIVERSAL IMAGE DENOISING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3616

Normal Similarity Network for Generative Modelling

Paper Details

Authors:
Jay Nandy, Wynne Hsu, Lee Mong Li
Submitted On:
8 October 2018 - 3:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip (2).pdf

(4)

Subscribe

[1] Jay Nandy, Wynne Hsu, Lee Mong Li, "Normal Similarity Network for Generative Modelling", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3614. Accessed: Apr. 25, 2019.
@article{3614-18,
url = {http://sigport.org/3614},
author = {Jay Nandy; Wynne Hsu; Lee Mong Li },
publisher = {IEEE SigPort},
title = {Normal Similarity Network for Generative Modelling},
year = {2018} }
TY - EJOUR
T1 - Normal Similarity Network for Generative Modelling
AU - Jay Nandy; Wynne Hsu; Lee Mong Li
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3614
ER -
Jay Nandy, Wynne Hsu, Lee Mong Li. (2018). Normal Similarity Network for Generative Modelling. IEEE SigPort. http://sigport.org/3614
Jay Nandy, Wynne Hsu, Lee Mong Li, 2018. Normal Similarity Network for Generative Modelling. Available at: http://sigport.org/3614.
Jay Nandy, Wynne Hsu, Lee Mong Li. (2018). "Normal Similarity Network for Generative Modelling." Web.
1. Jay Nandy, Wynne Hsu, Lee Mong Li. Normal Similarity Network for Generative Modelling [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3614

TOTAL VARIATION REGULARIZED REWEIGHTED LOW-RANK TENSOR COMPLETION FOR COLOR IMAGE INPAINTING


Recent low-rank based tensor completion (LRTC) algorithms have been successfully applied into color image inpainting. However, most of existing LRTC algorithms treat each dimension of tensors equally, which ignores the differences of the intrinsic structure correlations among dimensions. In this paper, we make a detailed analysis about the rank properties of each dimension and design a simple yet effective reweighted low-rank tensor completion model that truthfully capture the intrinsic structure correlations with reduced computational burden.

Paper Details

Authors:
Fei Jiang, Ruimin Shen
Submitted On:
8 October 2018 - 3:01am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP183018.pdf

(36)

Subscribe

[1] Fei Jiang, Ruimin Shen, "TOTAL VARIATION REGULARIZED REWEIGHTED LOW-RANK TENSOR COMPLETION FOR COLOR IMAGE INPAINTING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3612. Accessed: Apr. 25, 2019.
@article{3612-18,
url = {http://sigport.org/3612},
author = {Fei Jiang; Ruimin Shen },
publisher = {IEEE SigPort},
title = {TOTAL VARIATION REGULARIZED REWEIGHTED LOW-RANK TENSOR COMPLETION FOR COLOR IMAGE INPAINTING},
year = {2018} }
TY - EJOUR
T1 - TOTAL VARIATION REGULARIZED REWEIGHTED LOW-RANK TENSOR COMPLETION FOR COLOR IMAGE INPAINTING
AU - Fei Jiang; Ruimin Shen
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3612
ER -
Fei Jiang, Ruimin Shen. (2018). TOTAL VARIATION REGULARIZED REWEIGHTED LOW-RANK TENSOR COMPLETION FOR COLOR IMAGE INPAINTING. IEEE SigPort. http://sigport.org/3612
Fei Jiang, Ruimin Shen, 2018. TOTAL VARIATION REGULARIZED REWEIGHTED LOW-RANK TENSOR COMPLETION FOR COLOR IMAGE INPAINTING. Available at: http://sigport.org/3612.
Fei Jiang, Ruimin Shen. (2018). "TOTAL VARIATION REGULARIZED REWEIGHTED LOW-RANK TENSOR COMPLETION FOR COLOR IMAGE INPAINTING." Web.
1. Fei Jiang, Ruimin Shen. TOTAL VARIATION REGULARIZED REWEIGHTED LOW-RANK TENSOR COMPLETION FOR COLOR IMAGE INPAINTING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3612

Visual-Quality-driven Learning for Underwater Vision Enhancement


The image processing community has witnessed remarkable advances in enhancing and restoring images. Nevertheless, restoring the visual quality of underwater images remains a great challenge. End-to-end frameworks might fail to enhance the visual quality of underwater images since in several scenarios it is not feasible to provide the ground truth of the scene radiance. In this work, we propose a CNN-based approach that does not require ground truth data since it uses a set of image quality metrics to guide the restoration learning process.

Paper Details

Authors:
Walysson V Barbosa, Henrique G B Amaral, Thiago L Rocha, Erickson R Nascimento
Submitted On:
8 October 2018 - 2:42am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2018 (2).pdf

(3)

Subscribe

[1] Walysson V Barbosa, Henrique G B Amaral, Thiago L Rocha, Erickson R Nascimento, "Visual-Quality-driven Learning for Underwater Vision Enhancement", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3609. Accessed: Apr. 25, 2019.
@article{3609-18,
url = {http://sigport.org/3609},
author = {Walysson V Barbosa; Henrique G B Amaral; Thiago L Rocha; Erickson R Nascimento },
publisher = {IEEE SigPort},
title = {Visual-Quality-driven Learning for Underwater Vision Enhancement},
year = {2018} }
TY - EJOUR
T1 - Visual-Quality-driven Learning for Underwater Vision Enhancement
AU - Walysson V Barbosa; Henrique G B Amaral; Thiago L Rocha; Erickson R Nascimento
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3609
ER -
Walysson V Barbosa, Henrique G B Amaral, Thiago L Rocha, Erickson R Nascimento. (2018). Visual-Quality-driven Learning for Underwater Vision Enhancement. IEEE SigPort. http://sigport.org/3609
Walysson V Barbosa, Henrique G B Amaral, Thiago L Rocha, Erickson R Nascimento, 2018. Visual-Quality-driven Learning for Underwater Vision Enhancement. Available at: http://sigport.org/3609.
Walysson V Barbosa, Henrique G B Amaral, Thiago L Rocha, Erickson R Nascimento. (2018). "Visual-Quality-driven Learning for Underwater Vision Enhancement." Web.
1. Walysson V Barbosa, Henrique G B Amaral, Thiago L Rocha, Erickson R Nascimento. Visual-Quality-driven Learning for Underwater Vision Enhancement [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3609

A THREE-CATEGORY FACE DETECTOR WITH CONTEXTUAL INFORMATION ON FINDING TINY FACES


Great progresses have been achieved on object detection in the wild. However, it still remains a challenging problem due to tiny objects. In this paper, we present a Three-category Classification Neural Network to find tiny faces under complex environments by leveraging contextual information around faces. Tiny faces (within 20x20 pixels) are so fuzzy that the facial patterns are not clear or even ambiguous for detection.

Paper Details

Authors:
Feng Jiang, Jie Zhang, Liping Yan, Yuanqing Xia, Shiguang Shan
Submitted On:
8 October 2018 - 12:41am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster.pdf

(44)

Keywords

Additional Categories

Subscribe

[1] Feng Jiang, Jie Zhang, Liping Yan, Yuanqing Xia, Shiguang Shan, "A THREE-CATEGORY FACE DETECTOR WITH CONTEXTUAL INFORMATION ON FINDING TINY FACES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3607. Accessed: Apr. 25, 2019.
@article{3607-18,
url = {http://sigport.org/3607},
author = {Feng Jiang; Jie Zhang; Liping Yan; Yuanqing Xia; Shiguang Shan },
publisher = {IEEE SigPort},
title = {A THREE-CATEGORY FACE DETECTOR WITH CONTEXTUAL INFORMATION ON FINDING TINY FACES},
year = {2018} }
TY - EJOUR
T1 - A THREE-CATEGORY FACE DETECTOR WITH CONTEXTUAL INFORMATION ON FINDING TINY FACES
AU - Feng Jiang; Jie Zhang; Liping Yan; Yuanqing Xia; Shiguang Shan
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3607
ER -
Feng Jiang, Jie Zhang, Liping Yan, Yuanqing Xia, Shiguang Shan. (2018). A THREE-CATEGORY FACE DETECTOR WITH CONTEXTUAL INFORMATION ON FINDING TINY FACES. IEEE SigPort. http://sigport.org/3607
Feng Jiang, Jie Zhang, Liping Yan, Yuanqing Xia, Shiguang Shan, 2018. A THREE-CATEGORY FACE DETECTOR WITH CONTEXTUAL INFORMATION ON FINDING TINY FACES. Available at: http://sigport.org/3607.
Feng Jiang, Jie Zhang, Liping Yan, Yuanqing Xia, Shiguang Shan. (2018). "A THREE-CATEGORY FACE DETECTOR WITH CONTEXTUAL INFORMATION ON FINDING TINY FACES." Web.
1. Feng Jiang, Jie Zhang, Liping Yan, Yuanqing Xia, Shiguang Shan. A THREE-CATEGORY FACE DETECTOR WITH CONTEXTUAL INFORMATION ON FINDING TINY FACES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3607

A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST FUNCTION ANALYSIS

Paper Details

Authors:
Ron Op het Veld, Tobias Jaschke, Michel Bätz, Joachim Keinert
Submitted On:
7 October 2018 - 4:32pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation_ICIP_v2.pptx

(43)

Subscribe

[1] Ron Op het Veld, Tobias Jaschke, Michel Bätz, Joachim Keinert, "A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST FUNCTION ANALYSIS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3602. Accessed: Apr. 25, 2019.
@article{3602-18,
url = {http://sigport.org/3602},
author = {Ron Op het Veld; Tobias Jaschke; Michel Bätz; Joachim Keinert },
publisher = {IEEE SigPort},
title = {A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST FUNCTION ANALYSIS},
year = {2018} }
TY - EJOUR
T1 - A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST FUNCTION ANALYSIS
AU - Ron Op het Veld; Tobias Jaschke; Michel Bätz; Joachim Keinert
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3602
ER -
Ron Op het Veld, Tobias Jaschke, Michel Bätz, Joachim Keinert. (2018). A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST FUNCTION ANALYSIS. IEEE SigPort. http://sigport.org/3602
Ron Op het Veld, Tobias Jaschke, Michel Bätz, Joachim Keinert, 2018. A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST FUNCTION ANALYSIS. Available at: http://sigport.org/3602.
Ron Op het Veld, Tobias Jaschke, Michel Bätz, Joachim Keinert. (2018). "A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST FUNCTION ANALYSIS." Web.
1. Ron Op het Veld, Tobias Jaschke, Michel Bätz, Joachim Keinert. A NOVEL CONFIDENCE MEASURE FOR DISPARITY MAPS BY PIXEL-WISE COST FUNCTION ANALYSIS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3602

RTSeg: Real-time Semantic Segmentation Comparative Study

Paper Details

Authors:
Submitted On:
7 October 2018 - 3:57pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_Poster.pdf

(319)

Keywords

Additional Categories

Subscribe

[1] , "RTSeg: Real-time Semantic Segmentation Comparative Study", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3600. Accessed: Apr. 25, 2019.
@article{3600-18,
url = {http://sigport.org/3600},
author = { },
publisher = {IEEE SigPort},
title = {RTSeg: Real-time Semantic Segmentation Comparative Study},
year = {2018} }
TY - EJOUR
T1 - RTSeg: Real-time Semantic Segmentation Comparative Study
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3600
ER -
. (2018). RTSeg: Real-time Semantic Segmentation Comparative Study. IEEE SigPort. http://sigport.org/3600
, 2018. RTSeg: Real-time Semantic Segmentation Comparative Study. Available at: http://sigport.org/3600.
. (2018). "RTSeg: Real-time Semantic Segmentation Comparative Study." Web.
1. . RTSeg: Real-time Semantic Segmentation Comparative Study [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3600

A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting


Crowd counting, for estimating the number of people in a crowd using vision-based computer techniques, has attracted much interest in the research community. Although many attempts have been reported, real-world problems, such as huge variation in subjects’ sizes in images and serious occlusion among people, make it still a challenging problem. In this paper, we propose an Adaptive Counting Convolutional Neural Network (A-CCNN) and consider the scale variation of objects in a frame adaptively so as to improve the accuracy of counting.

Paper Details

Authors:
Saeed Amirgholipour, Xiangjian He, Wenjing Jia, Dadong Wang, Michelle Zeibots
Submitted On:
10 October 2018 - 7:26am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2018.pptx

(35)

Keywords

Additional Categories

Subscribe

[1] Saeed Amirgholipour, Xiangjian He, Wenjing Jia, Dadong Wang, Michelle Zeibots, "A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3599. Accessed: Apr. 25, 2019.
@article{3599-18,
url = {http://sigport.org/3599},
author = {Saeed Amirgholipour; Xiangjian He; Wenjing Jia; Dadong Wang; Michelle Zeibots },
publisher = {IEEE SigPort},
title = {A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting},
year = {2018} }
TY - EJOUR
T1 - A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting
AU - Saeed Amirgholipour; Xiangjian He; Wenjing Jia; Dadong Wang; Michelle Zeibots
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3599
ER -
Saeed Amirgholipour, Xiangjian He, Wenjing Jia, Dadong Wang, Michelle Zeibots. (2018). A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting. IEEE SigPort. http://sigport.org/3599
Saeed Amirgholipour, Xiangjian He, Wenjing Jia, Dadong Wang, Michelle Zeibots, 2018. A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting. Available at: http://sigport.org/3599.
Saeed Amirgholipour, Xiangjian He, Wenjing Jia, Dadong Wang, Michelle Zeibots. (2018). "A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting." Web.
1. Saeed Amirgholipour, Xiangjian He, Wenjing Jia, Dadong Wang, Michelle Zeibots. A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3599

IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES


A novel extension to proposal-based detection is proposed in order to learn convolutional context features for determining boundaries of objects better. Objects and their context are aimed to be learned through parallel convolutional stages. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection benchmark dataset and yielded improvements in performance over baseline, for all classes, especially the ones with distinctive context.

Paper Details

Authors:
Emre Can Kaya, A. Aydın Alatan
Submitted On:
7 October 2018 - 2:01pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

PosterPresentations.com-36x56-Template-V6.pdf

(64)

Keywords

Additional Categories

Subscribe

[1] Emre Can Kaya, A. Aydın Alatan, "IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3597. Accessed: Apr. 25, 2019.
@article{3597-18,
url = {http://sigport.org/3597},
author = {Emre Can Kaya; A. Aydın Alatan },
publisher = {IEEE SigPort},
title = {IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES},
year = {2018} }
TY - EJOUR
T1 - IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES
AU - Emre Can Kaya; A. Aydın Alatan
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3597
ER -
Emre Can Kaya, A. Aydın Alatan. (2018). IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES. IEEE SigPort. http://sigport.org/3597
Emre Can Kaya, A. Aydın Alatan, 2018. IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES. Available at: http://sigport.org/3597.
Emre Can Kaya, A. Aydın Alatan. (2018). "IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES." Web.
1. Emre Can Kaya, A. Aydın Alatan. IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3597

INDOOR DENSE DEPTH MAP AT DRONE HOVERING

Paper Details

Authors:
Arindam Saha, Soumyadip Maity, Brojeshwar Bhowmick
Submitted On:
7 October 2018 - 1:10pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation Slides

(6)

Subscribe

[1] Arindam Saha, Soumyadip Maity, Brojeshwar Bhowmick, "INDOOR DENSE DEPTH MAP AT DRONE HOVERING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3596. Accessed: Apr. 25, 2019.
@article{3596-18,
url = {http://sigport.org/3596},
author = {Arindam Saha; Soumyadip Maity; Brojeshwar Bhowmick },
publisher = {IEEE SigPort},
title = {INDOOR DENSE DEPTH MAP AT DRONE HOVERING},
year = {2018} }
TY - EJOUR
T1 - INDOOR DENSE DEPTH MAP AT DRONE HOVERING
AU - Arindam Saha; Soumyadip Maity; Brojeshwar Bhowmick
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3596
ER -
Arindam Saha, Soumyadip Maity, Brojeshwar Bhowmick. (2018). INDOOR DENSE DEPTH MAP AT DRONE HOVERING. IEEE SigPort. http://sigport.org/3596
Arindam Saha, Soumyadip Maity, Brojeshwar Bhowmick, 2018. INDOOR DENSE DEPTH MAP AT DRONE HOVERING. Available at: http://sigport.org/3596.
Arindam Saha, Soumyadip Maity, Brojeshwar Bhowmick. (2018). "INDOOR DENSE DEPTH MAP AT DRONE HOVERING." Web.
1. Arindam Saha, Soumyadip Maity, Brojeshwar Bhowmick. INDOOR DENSE DEPTH MAP AT DRONE HOVERING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3596

Pages