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

ICIP 2019

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.

EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE


Screen content videos (SCVs) are becoming popular in many applications. Compared with natural content videos (NCVs), the SCVs have different characteristics. Therefore, the screen content coding (SCC) based on HEVC adopts some new coding tools (intra block copy and palette mode etc.) to improve coding efficiency, but these tools increase the computational complexity as well. In this paper, we propose to predict the CU partition of the SCVs by a convolutional neural network

Paper Details

Authors:
zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen
Submitted On:
14 September 2019 - 4:27am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019_poster_L.Zhao

(3)

Subscribe

[1] zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen, "EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4614. Accessed: Sep. 15, 2019.
@article{4614-19,
url = {http://sigport.org/4614},
author = {zhiwen wei; weitong cai; wenyi wang; liaoyuan zeng and jianwen chen },
publisher = {IEEE SigPort},
title = {EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE},
year = {2019} }
TY - EJOUR
T1 - EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE
AU - zhiwen wei; weitong cai; wenyi wang; liaoyuan zeng and jianwen chen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4614
ER -
zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen. (2019). EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE. IEEE SigPort. http://sigport.org/4614
zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen, 2019. EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE. Available at: http://sigport.org/4614.
zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen. (2019). "EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE." Web.
1. zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen. EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4614

Two images comparison with invariance to illumination properties


A new way of performing pixel by pixel comparison between two images is proposed, taking advantage of interesting invariance properties with respect to illumination conditions and camera settings.

Paper Details

Authors:
Jean-Philippe Tarel
Submitted On:
13 September 2019 - 9:22am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

jpt_eposter.pdf

(4)

Keywords

Additional Categories

Subscribe

[1] Jean-Philippe Tarel, "Two images comparison with invariance to illumination properties", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4613. Accessed: Sep. 15, 2019.
@article{4613-19,
url = {http://sigport.org/4613},
author = {Jean-Philippe Tarel },
publisher = {IEEE SigPort},
title = {Two images comparison with invariance to illumination properties},
year = {2019} }
TY - EJOUR
T1 - Two images comparison with invariance to illumination properties
AU - Jean-Philippe Tarel
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4613
ER -
Jean-Philippe Tarel. (2019). Two images comparison with invariance to illumination properties. IEEE SigPort. http://sigport.org/4613
Jean-Philippe Tarel, 2019. Two images comparison with invariance to illumination properties. Available at: http://sigport.org/4613.
Jean-Philippe Tarel. (2019). "Two images comparison with invariance to illumination properties." Web.
1. Jean-Philippe Tarel. Two images comparison with invariance to illumination properties [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4613

Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks


Light field (LF) cameras often have significant limitations in spatial and angular resolutions due to their design. Many techniques that attempt to reconstruct LF images at a higher resolution only consider either spatial or angular resolution, but not both. We propose a generative network using high-dimensional convolution to improve both aspects. Our experimental results on both synthetic and real-world data demonstrate that the proposed model outperforms existing state-of-the-art methods in terms of both peak signal-to-noise ratio (PSNR) and visual quality.

Paper Details

Authors:
Nan Meng, Tianjiao Zeng, Edmund Y. Lam
Submitted On:
13 September 2019 - 9:14am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster for ICIP 2019

(8)

Keywords

Additional Categories

Subscribe

[1] Nan Meng, Tianjiao Zeng, Edmund Y. Lam, "Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4612. Accessed: Sep. 15, 2019.
@article{4612-19,
url = {http://sigport.org/4612},
author = {Nan Meng; Tianjiao Zeng; Edmund Y. Lam },
publisher = {IEEE SigPort},
title = {Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks},
year = {2019} }
TY - EJOUR
T1 - Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks
AU - Nan Meng; Tianjiao Zeng; Edmund Y. Lam
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4612
ER -
Nan Meng, Tianjiao Zeng, Edmund Y. Lam. (2019). Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks. IEEE SigPort. http://sigport.org/4612
Nan Meng, Tianjiao Zeng, Edmund Y. Lam, 2019. Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks. Available at: http://sigport.org/4612.
Nan Meng, Tianjiao Zeng, Edmund Y. Lam. (2019). "Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks." Web.
1. Nan Meng, Tianjiao Zeng, Edmund Y. Lam. Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4612

High-Resolution Class Activation Mapping


Insufficient reasoning for their predictions has for long been a major drawback of neural networks and has proved to be a major obstacle for their adoption by several fields of application. This paper presents a framework for discriminative localization, which helps shed some light into the decision-making of Convolutional Neural Networks (CNN). Our framework generates robust, refined and high-quality Class Activation Maps, without impacting the CNN’s performance.

Paper Details

Authors:
Thanos Tagaris, Maria Sdraka, Andreas Stafylopatis
Submitted On:
13 September 2019 - 5:46am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019_Poster.pdf

(4)

Keywords

Additional Categories

Subscribe

[1] Thanos Tagaris, Maria Sdraka, Andreas Stafylopatis, "High-Resolution Class Activation Mapping", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4611. Accessed: Sep. 15, 2019.
@article{4611-19,
url = {http://sigport.org/4611},
author = {Thanos Tagaris; Maria Sdraka; Andreas Stafylopatis },
publisher = {IEEE SigPort},
title = {High-Resolution Class Activation Mapping},
year = {2019} }
TY - EJOUR
T1 - High-Resolution Class Activation Mapping
AU - Thanos Tagaris; Maria Sdraka; Andreas Stafylopatis
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4611
ER -
Thanos Tagaris, Maria Sdraka, Andreas Stafylopatis. (2019). High-Resolution Class Activation Mapping. IEEE SigPort. http://sigport.org/4611
Thanos Tagaris, Maria Sdraka, Andreas Stafylopatis, 2019. High-Resolution Class Activation Mapping. Available at: http://sigport.org/4611.
Thanos Tagaris, Maria Sdraka, Andreas Stafylopatis. (2019). "High-Resolution Class Activation Mapping." Web.
1. Thanos Tagaris, Maria Sdraka, Andreas Stafylopatis. High-Resolution Class Activation Mapping [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4611

Estimation of correspondent trajectories in multiple overlapping synchronized videos using correlation of activity functions


We present an approach for ranking a collection of videos with overlapping fields of view. The ranking depends on how they allow to visualize as best as possible, i.e. with significant details, a trajectory query drawn in one of the videos. The proposed approach decomposes each video into cells and aims at estimating a correspondence map between cells from different videos using the linear correlation between their functions of activity.

Paper Details

Authors:
Sylvie Chambon, Vincent Charvillat, Alain Crouzil
Submitted On:
13 September 2019 - 5:31am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MalonThierry.pdf

(7)

Subscribe

[1] Sylvie Chambon, Vincent Charvillat, Alain Crouzil, "Estimation of correspondent trajectories in multiple overlapping synchronized videos using correlation of activity functions", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4610. Accessed: Sep. 15, 2019.
@article{4610-19,
url = {http://sigport.org/4610},
author = {Sylvie Chambon; Vincent Charvillat; Alain Crouzil },
publisher = {IEEE SigPort},
title = {Estimation of correspondent trajectories in multiple overlapping synchronized videos using correlation of activity functions},
year = {2019} }
TY - EJOUR
T1 - Estimation of correspondent trajectories in multiple overlapping synchronized videos using correlation of activity functions
AU - Sylvie Chambon; Vincent Charvillat; Alain Crouzil
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4610
ER -
Sylvie Chambon, Vincent Charvillat, Alain Crouzil. (2019). Estimation of correspondent trajectories in multiple overlapping synchronized videos using correlation of activity functions. IEEE SigPort. http://sigport.org/4610
Sylvie Chambon, Vincent Charvillat, Alain Crouzil, 2019. Estimation of correspondent trajectories in multiple overlapping synchronized videos using correlation of activity functions. Available at: http://sigport.org/4610.
Sylvie Chambon, Vincent Charvillat, Alain Crouzil. (2019). "Estimation of correspondent trajectories in multiple overlapping synchronized videos using correlation of activity functions." Web.
1. Sylvie Chambon, Vincent Charvillat, Alain Crouzil. Estimation of correspondent trajectories in multiple overlapping synchronized videos using correlation of activity functions [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4610

Towards Unsupervised Single Image Dehazing with Deep Learning


Deep learning computation is often used in single-image dehazing techniques for outdoor vision systems. Its development is restricted by the difficulties in providing a training set of degraded and ground-truth image pairs. In this paper, we develop a novel model that utilizes cycle generative adversarial network through unsupervised learning to effectively remove the requirement of a haze/depth data set. Qualitative and quantitative experiments demonstrated that the proposed model outperforms existing state-of-the-art dehazing models when tested on both synthetic and real haze images.

Paper Details

Authors:
Lu-Yao Huang, Jia-Li Yin, Bo-Hao Chen, and Shao-Zhen Ye
Submitted On:
13 September 2019 - 4:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_2019_dehazing(1).pdf

(7)

Keywords

Additional Categories

Subscribe

[1] Lu-Yao Huang, Jia-Li Yin, Bo-Hao Chen, and Shao-Zhen Ye, "Towards Unsupervised Single Image Dehazing with Deep Learning", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4609. Accessed: Sep. 15, 2019.
@article{4609-19,
url = {http://sigport.org/4609},
author = {Lu-Yao Huang; Jia-Li Yin; Bo-Hao Chen; and Shao-Zhen Ye },
publisher = {IEEE SigPort},
title = {Towards Unsupervised Single Image Dehazing with Deep Learning},
year = {2019} }
TY - EJOUR
T1 - Towards Unsupervised Single Image Dehazing with Deep Learning
AU - Lu-Yao Huang; Jia-Li Yin; Bo-Hao Chen; and Shao-Zhen Ye
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4609
ER -
Lu-Yao Huang, Jia-Li Yin, Bo-Hao Chen, and Shao-Zhen Ye. (2019). Towards Unsupervised Single Image Dehazing with Deep Learning. IEEE SigPort. http://sigport.org/4609
Lu-Yao Huang, Jia-Li Yin, Bo-Hao Chen, and Shao-Zhen Ye, 2019. Towards Unsupervised Single Image Dehazing with Deep Learning. Available at: http://sigport.org/4609.
Lu-Yao Huang, Jia-Li Yin, Bo-Hao Chen, and Shao-Zhen Ye. (2019). "Towards Unsupervised Single Image Dehazing with Deep Learning." Web.
1. Lu-Yao Huang, Jia-Li Yin, Bo-Hao Chen, and Shao-Zhen Ye. Towards Unsupervised Single Image Dehazing with Deep Learning [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4609

Image smoothing via gradient sparsity and surface area minimization


Image smoothing is a very important topic in image processing. Among these image smoothing methods, the $L_0$ gradient minimization method is one of the most popular ones. However, the $L_0$ gradient minimization method suffers from the staircasing effect and over-sharpening issue, which highly degrade the quality of the smoothed image. To overcome these issues, we use not only the $L_0$ gradient term for finding edges, but also a surface area based term for the purpose of smoothing the inside of each region.

Paper Details

Authors:
Ming Yan, Jinshan Zeng, Tieyong Zeng
Submitted On:
13 September 2019 - 4:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster PPT

(7)

Subscribe

[1] Ming Yan, Jinshan Zeng, Tieyong Zeng, "Image smoothing via gradient sparsity and surface area minimization", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4608. Accessed: Sep. 15, 2019.
@article{4608-19,
url = {http://sigport.org/4608},
author = {Ming Yan; Jinshan Zeng; Tieyong Zeng },
publisher = {IEEE SigPort},
title = {Image smoothing via gradient sparsity and surface area minimization},
year = {2019} }
TY - EJOUR
T1 - Image smoothing via gradient sparsity and surface area minimization
AU - Ming Yan; Jinshan Zeng; Tieyong Zeng
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4608
ER -
Ming Yan, Jinshan Zeng, Tieyong Zeng. (2019). Image smoothing via gradient sparsity and surface area minimization. IEEE SigPort. http://sigport.org/4608
Ming Yan, Jinshan Zeng, Tieyong Zeng, 2019. Image smoothing via gradient sparsity and surface area minimization. Available at: http://sigport.org/4608.
Ming Yan, Jinshan Zeng, Tieyong Zeng. (2019). "Image smoothing via gradient sparsity and surface area minimization." Web.
1. Ming Yan, Jinshan Zeng, Tieyong Zeng. Image smoothing via gradient sparsity and surface area minimization [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4608

5D Video Stabilization through Sensor Vision Fusion

Paper Details

Authors:
Binnan Zhuang, Dongwoon Bai, Jungwon Lee
Submitted On:
13 September 2019 - 2:30am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

5D Stabilization ICIP 2019.pdf

(5)

Subscribe

[1] Binnan Zhuang, Dongwoon Bai, Jungwon Lee, "5D Video Stabilization through Sensor Vision Fusion", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4607. Accessed: Sep. 15, 2019.
@article{4607-19,
url = {http://sigport.org/4607},
author = {Binnan Zhuang; Dongwoon Bai; Jungwon Lee },
publisher = {IEEE SigPort},
title = {5D Video Stabilization through Sensor Vision Fusion},
year = {2019} }
TY - EJOUR
T1 - 5D Video Stabilization through Sensor Vision Fusion
AU - Binnan Zhuang; Dongwoon Bai; Jungwon Lee
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4607
ER -
Binnan Zhuang, Dongwoon Bai, Jungwon Lee. (2019). 5D Video Stabilization through Sensor Vision Fusion. IEEE SigPort. http://sigport.org/4607
Binnan Zhuang, Dongwoon Bai, Jungwon Lee, 2019. 5D Video Stabilization through Sensor Vision Fusion. Available at: http://sigport.org/4607.
Binnan Zhuang, Dongwoon Bai, Jungwon Lee. (2019). "5D Video Stabilization through Sensor Vision Fusion." Web.
1. Binnan Zhuang, Dongwoon Bai, Jungwon Lee. 5D Video Stabilization through Sensor Vision Fusion [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4607

Fashion Recommendation on Street Images


Learning the compatibility relationship is of vital importance to a fashion recommendation system, while existing works achieve this merely on product images but not on street images in the complex daily life scenario. In this paper, we propose a novel fashion recommendation system: Given a query item of interest in the street scenario, the system can return the compatible items. More specifically, a two-stage curriculum learning scheme is developed to transfer the semantics from the product to street outfit images.

Paper Details

Authors:
Zhan Huijing, Shi Boxin, Chen Jiawei, Zheng Qian, Duan Lingyu Alex C. Kot
Submitted On:
13 September 2019 - 12:13am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip_poster_draft_0901.pptx

(3)

Subscribe

[1] Zhan Huijing, Shi Boxin, Chen Jiawei, Zheng Qian, Duan Lingyu Alex C. Kot, "Fashion Recommendation on Street Images", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4606. Accessed: Sep. 15, 2019.
@article{4606-19,
url = {http://sigport.org/4606},
author = {Zhan Huijing; Shi Boxin; Chen Jiawei; Zheng Qian; Duan Lingyu Alex C. Kot },
publisher = {IEEE SigPort},
title = {Fashion Recommendation on Street Images},
year = {2019} }
TY - EJOUR
T1 - Fashion Recommendation on Street Images
AU - Zhan Huijing; Shi Boxin; Chen Jiawei; Zheng Qian; Duan Lingyu Alex C. Kot
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4606
ER -
Zhan Huijing, Shi Boxin, Chen Jiawei, Zheng Qian, Duan Lingyu Alex C. Kot. (2019). Fashion Recommendation on Street Images. IEEE SigPort. http://sigport.org/4606
Zhan Huijing, Shi Boxin, Chen Jiawei, Zheng Qian, Duan Lingyu Alex C. Kot, 2019. Fashion Recommendation on Street Images. Available at: http://sigport.org/4606.
Zhan Huijing, Shi Boxin, Chen Jiawei, Zheng Qian, Duan Lingyu Alex C. Kot. (2019). "Fashion Recommendation on Street Images." Web.
1. Zhan Huijing, Shi Boxin, Chen Jiawei, Zheng Qian, Duan Lingyu Alex C. Kot. Fashion Recommendation on Street Images [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4606

Temporal Interframe Pattern Analysis for Static and Dynamic Hand Gesture Recognition


Hand gesture, a common non-verbal language, is being studied for Human Computer Interaction. Hand gestures can be categorized as static hand gestures and dynamic hand gestures. In recent years, effective approaches have been applied to hand gesture recognition.

Paper Details

Authors:
Lijun Yin, Tianyang Wang
Submitted On:
12 September 2019 - 12:13pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

eposter_Paper_2652_Kaoning_Hu.pdf

(4)

Subscribe

[1] Lijun Yin, Tianyang Wang, "Temporal Interframe Pattern Analysis for Static and Dynamic Hand Gesture Recognition", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4605. Accessed: Sep. 15, 2019.
@article{4605-19,
url = {http://sigport.org/4605},
author = {Lijun Yin; Tianyang Wang },
publisher = {IEEE SigPort},
title = {Temporal Interframe Pattern Analysis for Static and Dynamic Hand Gesture Recognition},
year = {2019} }
TY - EJOUR
T1 - Temporal Interframe Pattern Analysis for Static and Dynamic Hand Gesture Recognition
AU - Lijun Yin; Tianyang Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4605
ER -
Lijun Yin, Tianyang Wang. (2019). Temporal Interframe Pattern Analysis for Static and Dynamic Hand Gesture Recognition. IEEE SigPort. http://sigport.org/4605
Lijun Yin, Tianyang Wang, 2019. Temporal Interframe Pattern Analysis for Static and Dynamic Hand Gesture Recognition. Available at: http://sigport.org/4605.
Lijun Yin, Tianyang Wang. (2019). "Temporal Interframe Pattern Analysis for Static and Dynamic Hand Gesture Recognition." Web.
1. Lijun Yin, Tianyang Wang. Temporal Interframe Pattern Analysis for Static and Dynamic Hand Gesture Recognition [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4605

Pages