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

ICIP 2020

ICIP 2020 is a fully virtual conference. The International Conference on Image Processing (ICIP), sponsored by the IEEE Signal Processing Society, is the premier forum for the presentation of technological advances and research results in the fields of theoretical, experimental, and applied image and video processing. ICIP has been held annually since 1994, brings together leading engineers and scientists in image and video processing from around the world. Visit website

AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION


Texture is an indispensable property to develop many vision
based autonomous applications. Compared to colour, feature
dimension in a local texture descriptor is quite large as dense
texture features need to represent the distribution of pixel intensities
in the neighbourhood of each pixel. Large dimensional
features require additional time for further processing
that often restrict real-time applications. In this paper, a robust
local texture descriptor is enhanced by reducing feature

Paper Details

Authors:
Manzur Murshed, Shyh Wei Teng, Gour Karmakar
Submitted On:
3 November 2020 - 11:06pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

OralPresentationSlide_PaperID_2389.pptx

(7)

Subscribe

[1] Manzur Murshed, Shyh Wei Teng, Gour Karmakar, "AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5527. Accessed: Nov. 26, 2020.
@article{5527-20,
url = {http://sigport.org/5527},
author = {Manzur Murshed; Shyh Wei Teng; Gour Karmakar },
publisher = {IEEE SigPort},
title = {AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION},
year = {2020} }
TY - EJOUR
T1 - AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION
AU - Manzur Murshed; Shyh Wei Teng; Gour Karmakar
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5527
ER -
Manzur Murshed, Shyh Wei Teng, Gour Karmakar. (2020). AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION. IEEE SigPort. http://sigport.org/5527
Manzur Murshed, Shyh Wei Teng, Gour Karmakar, 2020. AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION. Available at: http://sigport.org/5527.
Manzur Murshed, Shyh Wei Teng, Gour Karmakar. (2020). "AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION." Web.
1. Manzur Murshed, Shyh Wei Teng, Gour Karmakar. AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5527

ICIP 2020 presentation slides

Paper Details

Authors:
Submitted On:
3 November 2020 - 10:24pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP-ppt.pptx

(7)

Subscribe

[1] , "ICIP 2020 presentation slides", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5526. Accessed: Nov. 26, 2020.
@article{5526-20,
url = {http://sigport.org/5526},
author = { },
publisher = {IEEE SigPort},
title = {ICIP 2020 presentation slides},
year = {2020} }
TY - EJOUR
T1 - ICIP 2020 presentation slides
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5526
ER -
. (2020). ICIP 2020 presentation slides. IEEE SigPort. http://sigport.org/5526
, 2020. ICIP 2020 presentation slides. Available at: http://sigport.org/5526.
. (2020). "ICIP 2020 presentation slides." Web.
1. . ICIP 2020 presentation slides [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5526

Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization


Ocular biometric systems working in unconstrained environments usually face the problem of small within-class compactness caused by the multiple factors that jointly degrade the quality of the obtained data. In this work, we propose an attribute normalization strategy based on deep learning generative frameworks, that reduces the variability of the samples used in pairwise comparisons, without reducing their discriminability.

Paper Details

Authors:
Luiz A. Zanlorensi, Hugo Proença, David Menotti
Submitted On:
3 November 2020 - 5:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

zanlorensi2020attgan.pdf

(5)

Keywords

Subscribe

[1] Luiz A. Zanlorensi, Hugo Proença, David Menotti, "Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5525. Accessed: Nov. 26, 2020.
@article{5525-20,
url = {http://sigport.org/5525},
author = {Luiz A. Zanlorensi; Hugo Proença; David Menotti },
publisher = {IEEE SigPort},
title = {Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization},
year = {2020} }
TY - EJOUR
T1 - Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization
AU - Luiz A. Zanlorensi; Hugo Proença; David Menotti
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5525
ER -
Luiz A. Zanlorensi, Hugo Proença, David Menotti. (2020). Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization. IEEE SigPort. http://sigport.org/5525
Luiz A. Zanlorensi, Hugo Proença, David Menotti, 2020. Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization. Available at: http://sigport.org/5525.
Luiz A. Zanlorensi, Hugo Proença, David Menotti. (2020). "Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization." Web.
1. Luiz A. Zanlorensi, Hugo Proença, David Menotti. Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5525

Memory Assessment of Versatile Video Coding


This work presents a memory assessment of the next-generation Versatile Video Coding (VVC). The memory analyses are performed adopting as a baseline the state-of-the-art High-Efficiency Video Coding (HEVC). The goal is to offer insights and observations of how critical the memory requirements of VVC are aggravated, compared to HEVC. The adopted methodology consists of two sets of experiments: (1) an overall memory profiling and (2) an inter-prediction specific memory analysis. The results obtained in the memory profiling show that VVC access up to 13.4x more memory than HEVC.

Paper Details

Authors:
Arthur Cerveira, Luciano Agostini, Bruno Zatt, Felipe Sampaio
Submitted On:
3 November 2020 - 3:27pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

VVC Memory Analysis.pdf

(4)

Subscribe

[1] Arthur Cerveira, Luciano Agostini, Bruno Zatt, Felipe Sampaio, "Memory Assessment of Versatile Video Coding", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5524. Accessed: Nov. 26, 2020.
@article{5524-20,
url = {http://sigport.org/5524},
author = {Arthur Cerveira; Luciano Agostini; Bruno Zatt; Felipe Sampaio },
publisher = {IEEE SigPort},
title = {Memory Assessment of Versatile Video Coding},
year = {2020} }
TY - EJOUR
T1 - Memory Assessment of Versatile Video Coding
AU - Arthur Cerveira; Luciano Agostini; Bruno Zatt; Felipe Sampaio
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5524
ER -
Arthur Cerveira, Luciano Agostini, Bruno Zatt, Felipe Sampaio. (2020). Memory Assessment of Versatile Video Coding. IEEE SigPort. http://sigport.org/5524
Arthur Cerveira, Luciano Agostini, Bruno Zatt, Felipe Sampaio, 2020. Memory Assessment of Versatile Video Coding. Available at: http://sigport.org/5524.
Arthur Cerveira, Luciano Agostini, Bruno Zatt, Felipe Sampaio. (2020). "Memory Assessment of Versatile Video Coding." Web.
1. Arthur Cerveira, Luciano Agostini, Bruno Zatt, Felipe Sampaio. Memory Assessment of Versatile Video Coding [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5524

Complexity Analysis of VVC Intra Prediction

Paper Details

Authors:
Mário Saldanha, Gustavo Sanchez, César Marcon, Luciano Agostini
Submitted On:
3 November 2020 - 1:44pm
Short Link:
Type:
Event:

Document Files

presentation.pdf

(7)

Keywords

Subscribe

[1] Mário Saldanha, Gustavo Sanchez, César Marcon, Luciano Agostini, "Complexity Analysis of VVC Intra Prediction", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5523. Accessed: Nov. 26, 2020.
@article{5523-20,
url = {http://sigport.org/5523},
author = {Mário Saldanha; Gustavo Sanchez; César Marcon; Luciano Agostini },
publisher = {IEEE SigPort},
title = {Complexity Analysis of VVC Intra Prediction},
year = {2020} }
TY - EJOUR
T1 - Complexity Analysis of VVC Intra Prediction
AU - Mário Saldanha; Gustavo Sanchez; César Marcon; Luciano Agostini
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5523
ER -
Mário Saldanha, Gustavo Sanchez, César Marcon, Luciano Agostini. (2020). Complexity Analysis of VVC Intra Prediction. IEEE SigPort. http://sigport.org/5523
Mário Saldanha, Gustavo Sanchez, César Marcon, Luciano Agostini, 2020. Complexity Analysis of VVC Intra Prediction. Available at: http://sigport.org/5523.
Mário Saldanha, Gustavo Sanchez, César Marcon, Luciano Agostini. (2020). "Complexity Analysis of VVC Intra Prediction." Web.
1. Mário Saldanha, Gustavo Sanchez, César Marcon, Luciano Agostini. Complexity Analysis of VVC Intra Prediction [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5523

One-Shot Layer-Wise Accuracy Approximation for Layer Pruning


Recent advances in neural networks pruning have made it possible to remove a large number of filters without any perceptible drop in accuracy. However, the gain in speed depends on the number of filters per layer. In this paper, we propose a one-shot layer-wise proxy classifier to estimate layer importance that in turn allows us to prune a whole layer. In contrast to existing filter pruning methods which attempt to reduce the layer width of a dense model, our method reduces its depth and can thus guarantee inference speed up.

Paper Details

Authors:
Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang, Nilanjan Ray
Submitted On:
3 November 2020 - 11:45am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICIP20-1736-One-Shot Layer-Wise Accuracy Approximation for Layer Pruning.pdf

(4)

Keywords

Additional Categories

Subscribe

[1] Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang, Nilanjan Ray, "One-Shot Layer-Wise Accuracy Approximation for Layer Pruning", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5522. Accessed: Nov. 26, 2020.
@article{5522-20,
url = {http://sigport.org/5522},
author = {Sara Elkerdawy; Mostafa Elhoushi; Abhineet Singh; Hong Zhang; Nilanjan Ray },
publisher = {IEEE SigPort},
title = {One-Shot Layer-Wise Accuracy Approximation for Layer Pruning},
year = {2020} }
TY - EJOUR
T1 - One-Shot Layer-Wise Accuracy Approximation for Layer Pruning
AU - Sara Elkerdawy; Mostafa Elhoushi; Abhineet Singh; Hong Zhang; Nilanjan Ray
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5522
ER -
Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang, Nilanjan Ray. (2020). One-Shot Layer-Wise Accuracy Approximation for Layer Pruning. IEEE SigPort. http://sigport.org/5522
Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang, Nilanjan Ray, 2020. One-Shot Layer-Wise Accuracy Approximation for Layer Pruning. Available at: http://sigport.org/5522.
Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang, Nilanjan Ray. (2020). "One-Shot Layer-Wise Accuracy Approximation for Layer Pruning." Web.
1. Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang, Nilanjan Ray. One-Shot Layer-Wise Accuracy Approximation for Layer Pruning [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5522

An enhanced deep learning architecture for classification of tuberculosis types from CT lung images

Paper Details

Authors:
Xiaohong Gao, Richard Compley, Maleika Heenaye-Mamode Khan
Submitted On:
3 November 2020 - 9:39am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2020-10-ICIP2020-Slides.pdf

(4)

Subscribe

[1] Xiaohong Gao, Richard Compley, Maleika Heenaye-Mamode Khan , "An enhanced deep learning architecture for classification of tuberculosis types from CT lung images", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5521. Accessed: Nov. 26, 2020.
@article{5521-20,
url = {http://sigport.org/5521},
author = {Xiaohong Gao; Richard Compley; Maleika Heenaye-Mamode Khan },
publisher = {IEEE SigPort},
title = {An enhanced deep learning architecture for classification of tuberculosis types from CT lung images},
year = {2020} }
TY - EJOUR
T1 - An enhanced deep learning architecture for classification of tuberculosis types from CT lung images
AU - Xiaohong Gao; Richard Compley; Maleika Heenaye-Mamode Khan
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5521
ER -
Xiaohong Gao, Richard Compley, Maleika Heenaye-Mamode Khan . (2020). An enhanced deep learning architecture for classification of tuberculosis types from CT lung images. IEEE SigPort. http://sigport.org/5521
Xiaohong Gao, Richard Compley, Maleika Heenaye-Mamode Khan , 2020. An enhanced deep learning architecture for classification of tuberculosis types from CT lung images. Available at: http://sigport.org/5521.
Xiaohong Gao, Richard Compley, Maleika Heenaye-Mamode Khan . (2020). "An enhanced deep learning architecture for classification of tuberculosis types from CT lung images." Web.
1. Xiaohong Gao, Richard Compley, Maleika Heenaye-Mamode Khan . An enhanced deep learning architecture for classification of tuberculosis types from CT lung images [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5521

Deep Regression Forest with Soft-Attention for Head Pose Estimation


The task of head pose estimation from a single depth image is challenging, due to the presence of large pose variations, occlusions and inhomegeneous facial feature space. To solve the problem, we propose Deep Regression Forest with Soft-Attention (SA-DRF) in a multi-task learning setup. It can be integrated with a general feature learning net and jointly learned in an end-to-end manner. The soft-attention module is facilitated to learn soft masks from the general features and feeds the forest with task-specific features to regress head poses.

Paper Details

Authors:
Xiangtian Ma, Nan Sang, Xupeng Wang, Shihua Xiao
Submitted On:
3 November 2020 - 9:48am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP2020_paper2985_slides.pptx

(10)

Subscribe

[1] Xiangtian Ma, Nan Sang, Xupeng Wang, Shihua Xiao, "Deep Regression Forest with Soft-Attention for Head Pose Estimation", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5520. Accessed: Nov. 26, 2020.
@article{5520-20,
url = {http://sigport.org/5520},
author = {Xiangtian Ma; Nan Sang; Xupeng Wang; Shihua Xiao },
publisher = {IEEE SigPort},
title = {Deep Regression Forest with Soft-Attention for Head Pose Estimation},
year = {2020} }
TY - EJOUR
T1 - Deep Regression Forest with Soft-Attention for Head Pose Estimation
AU - Xiangtian Ma; Nan Sang; Xupeng Wang; Shihua Xiao
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5520
ER -
Xiangtian Ma, Nan Sang, Xupeng Wang, Shihua Xiao. (2020). Deep Regression Forest with Soft-Attention for Head Pose Estimation. IEEE SigPort. http://sigport.org/5520
Xiangtian Ma, Nan Sang, Xupeng Wang, Shihua Xiao, 2020. Deep Regression Forest with Soft-Attention for Head Pose Estimation. Available at: http://sigport.org/5520.
Xiangtian Ma, Nan Sang, Xupeng Wang, Shihua Xiao. (2020). "Deep Regression Forest with Soft-Attention for Head Pose Estimation." Web.
1. Xiangtian Ma, Nan Sang, Xupeng Wang, Shihua Xiao. Deep Regression Forest with Soft-Attention for Head Pose Estimation [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5520

Model Uncertainty for Unsupervised Domain Adaptation


The key principle of unsupervised domain adaptation is to minimize the divergence between source and target domain. Many recent methods follow this principle to learn domain-invariant features. They train task-specific classifiers to maximize the divergence and feature extractors to minimize the divergence in an adversarial way. However, this strategy often limits their performance. In this paper, we present a novel method that learns feature representations that minimize the domain divergence. We show that model uncertainty is a useful surrogate for the domain divergence.

Paper Details

Authors:
JoonHo Lee, Gyemin Lee
Submitted On:
3 November 2020 - 8:50am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP-2020-2684 presentation slide

(8)

Subscribe

[1] JoonHo Lee, Gyemin Lee, "Model Uncertainty for Unsupervised Domain Adaptation", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5519. Accessed: Nov. 26, 2020.
@article{5519-20,
url = {http://sigport.org/5519},
author = {JoonHo Lee; Gyemin Lee },
publisher = {IEEE SigPort},
title = {Model Uncertainty for Unsupervised Domain Adaptation},
year = {2020} }
TY - EJOUR
T1 - Model Uncertainty for Unsupervised Domain Adaptation
AU - JoonHo Lee; Gyemin Lee
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5519
ER -
JoonHo Lee, Gyemin Lee. (2020). Model Uncertainty for Unsupervised Domain Adaptation. IEEE SigPort. http://sigport.org/5519
JoonHo Lee, Gyemin Lee, 2020. Model Uncertainty for Unsupervised Domain Adaptation. Available at: http://sigport.org/5519.
JoonHo Lee, Gyemin Lee. (2020). "Model Uncertainty for Unsupervised Domain Adaptation." Web.
1. JoonHo Lee, Gyemin Lee. Model Uncertainty for Unsupervised Domain Adaptation [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5519

RSANET: Deep Recurrent Scale-aware Network for Crowd Counting

Paper Details

Authors:
Yujun Xie, Yao Lu, Shunzhou Wang
Submitted On:
3 November 2020 - 7:38am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2020-YujunXie.pdf

(7)

Subscribe

[1] Yujun Xie, Yao Lu, Shunzhou Wang, "RSANET: Deep Recurrent Scale-aware Network for Crowd Counting", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5518. Accessed: Nov. 26, 2020.
@article{5518-20,
url = {http://sigport.org/5518},
author = {Yujun Xie; Yao Lu; Shunzhou Wang },
publisher = {IEEE SigPort},
title = {RSANET: Deep Recurrent Scale-aware Network for Crowd Counting},
year = {2020} }
TY - EJOUR
T1 - RSANET: Deep Recurrent Scale-aware Network for Crowd Counting
AU - Yujun Xie; Yao Lu; Shunzhou Wang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5518
ER -
Yujun Xie, Yao Lu, Shunzhou Wang. (2020). RSANET: Deep Recurrent Scale-aware Network for Crowd Counting. IEEE SigPort. http://sigport.org/5518
Yujun Xie, Yao Lu, Shunzhou Wang, 2020. RSANET: Deep Recurrent Scale-aware Network for Crowd Counting. Available at: http://sigport.org/5518.
Yujun Xie, Yao Lu, Shunzhou Wang. (2020). "RSANET: Deep Recurrent Scale-aware Network for Crowd Counting." Web.
1. Yujun Xie, Yao Lu, Shunzhou Wang. RSANET: Deep Recurrent Scale-aware Network for Crowd Counting [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5518

Pages