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

3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements


A 3D point cloud is often synthesized from depth measurements collected by sensors at different viewpoints. The acquired measurements are typically both coarse in precision and corrupted by noise. To improve quality, previous works denoise a synthesized 3D point cloud a posteriori, after projecting the imperfect depth data onto the 3D space. Instead, we enhance depth measurements on the sensed images a priori, exploiting inherent 3D geometric correlation across views, before synthesizing a 3D point cloud from the improved measurements.

Paper Details

Authors:
Xue Zhang, Gene Cheung, Jiahao Pang, Dong Tian
Submitted On:
2 November 2020 - 11:51am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements

(7)

Subscribe

[1] Xue Zhang, Gene Cheung, Jiahao Pang, Dong Tian, "3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5476. Accessed: Nov. 29, 2020.
@article{5476-20,
url = {http://sigport.org/5476},
author = {Xue Zhang; Gene Cheung; Jiahao Pang; Dong Tian },
publisher = {IEEE SigPort},
title = {3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements},
year = {2020} }
TY - EJOUR
T1 - 3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements
AU - Xue Zhang; Gene Cheung; Jiahao Pang; Dong Tian
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5476
ER -
Xue Zhang, Gene Cheung, Jiahao Pang, Dong Tian. (2020). 3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements. IEEE SigPort. http://sigport.org/5476
Xue Zhang, Gene Cheung, Jiahao Pang, Dong Tian, 2020. 3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements. Available at: http://sigport.org/5476.
Xue Zhang, Gene Cheung, Jiahao Pang, Dong Tian. (2020). "3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements." Web.
1. Xue Zhang, Gene Cheung, Jiahao Pang, Dong Tian. 3D Point Cloud Enhancement using Graph-Modelled Multiview Depth Measurements [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5476

Semantic Preserving Image Compression


Video traffic comprises a large majority of the total traffic on the internet today. Uncompressed visual data requires a very large data rate; lossy compression techniques are employed in order to keep the data-rate manageable. Increasingly, a significant amount of visual data being generated is consumed by analytics (such as classification, detection, etc.) residing in the cloud. Image and video compression can produce visual artifacts, especially at lower data-rates, which can result in a significant drop in performance on such analytic tasks.

Paper Details

Authors:
Neel Patwa, Nilesh Ahuja, Srinivasa Somayazulu, Omesh Tickoo, Srenivas Varadarajan, Shashidhar Koolagudi
Submitted On:
2 November 2020 - 11:51am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

SPIC_ICIP_2020.pdf

(10)

Keywords

Additional Categories

Subscribe

[1] Neel Patwa, Nilesh Ahuja, Srinivasa Somayazulu, Omesh Tickoo, Srenivas Varadarajan, Shashidhar Koolagudi, "Semantic Preserving Image Compression", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5475. Accessed: Nov. 29, 2020.
@article{5475-20,
url = {http://sigport.org/5475},
author = {Neel Patwa; Nilesh Ahuja; Srinivasa Somayazulu; Omesh Tickoo; Srenivas Varadarajan; Shashidhar Koolagudi },
publisher = {IEEE SigPort},
title = {Semantic Preserving Image Compression},
year = {2020} }
TY - EJOUR
T1 - Semantic Preserving Image Compression
AU - Neel Patwa; Nilesh Ahuja; Srinivasa Somayazulu; Omesh Tickoo; Srenivas Varadarajan; Shashidhar Koolagudi
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5475
ER -
Neel Patwa, Nilesh Ahuja, Srinivasa Somayazulu, Omesh Tickoo, Srenivas Varadarajan, Shashidhar Koolagudi. (2020). Semantic Preserving Image Compression. IEEE SigPort. http://sigport.org/5475
Neel Patwa, Nilesh Ahuja, Srinivasa Somayazulu, Omesh Tickoo, Srenivas Varadarajan, Shashidhar Koolagudi, 2020. Semantic Preserving Image Compression. Available at: http://sigport.org/5475.
Neel Patwa, Nilesh Ahuja, Srinivasa Somayazulu, Omesh Tickoo, Srenivas Varadarajan, Shashidhar Koolagudi. (2020). "Semantic Preserving Image Compression." Web.
1. Neel Patwa, Nilesh Ahuja, Srinivasa Somayazulu, Omesh Tickoo, Srenivas Varadarajan, Shashidhar Koolagudi. Semantic Preserving Image Compression [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5475

slides of ICIP 2020 Paper #3114: QUALITY EVALUATION OF DIGITAL HOLOGRAPHIC DATA ENCODED ON THE OBJECT PLANE USING STATE OF THE ART CODECS

Paper Details

Authors:
Submitted On:
2 November 2020 - 11:50am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

PRJ-ICIP20-Holo4pdf.pdf

(11)

Subscribe

[1] , "slides of ICIP 2020 Paper #3114: QUALITY EVALUATION OF DIGITAL HOLOGRAPHIC DATA ENCODED ON THE OBJECT PLANE USING STATE OF THE ART CODECS", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5474. Accessed: Nov. 29, 2020.
@article{5474-20,
url = {http://sigport.org/5474},
author = { },
publisher = {IEEE SigPort},
title = {slides of ICIP 2020 Paper #3114: QUALITY EVALUATION OF DIGITAL HOLOGRAPHIC DATA ENCODED ON THE OBJECT PLANE USING STATE OF THE ART CODECS},
year = {2020} }
TY - EJOUR
T1 - slides of ICIP 2020 Paper #3114: QUALITY EVALUATION OF DIGITAL HOLOGRAPHIC DATA ENCODED ON THE OBJECT PLANE USING STATE OF THE ART CODECS
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5474
ER -
. (2020). slides of ICIP 2020 Paper #3114: QUALITY EVALUATION OF DIGITAL HOLOGRAPHIC DATA ENCODED ON THE OBJECT PLANE USING STATE OF THE ART CODECS. IEEE SigPort. http://sigport.org/5474
, 2020. slides of ICIP 2020 Paper #3114: QUALITY EVALUATION OF DIGITAL HOLOGRAPHIC DATA ENCODED ON THE OBJECT PLANE USING STATE OF THE ART CODECS. Available at: http://sigport.org/5474.
. (2020). "slides of ICIP 2020 Paper #3114: QUALITY EVALUATION OF DIGITAL HOLOGRAPHIC DATA ENCODED ON THE OBJECT PLANE USING STATE OF THE ART CODECS." Web.
1. . slides of ICIP 2020 Paper #3114: QUALITY EVALUATION OF DIGITAL HOLOGRAPHIC DATA ENCODED ON THE OBJECT PLANE USING STATE OF THE ART CODECS [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5474

DEPTH ESTIMATION FROM SINGLE IMAGE AND SEMANTIC PRIOR


The multi-modality sensor fusion technique is an active research
area in scene understating. In this work, we explore
the RGB image and semantic-map fusion methods for depth
estimation. The LiDARs, Kinect, and TOF depth sensors are
unable to predict the depth-map at illuminate and monotonous
pattern surface. In this paper, we propose a semantic-to-depth
generative adversarial network (S2D-GAN) for depth estimation
from RGB image and its semantic-map. In the first stage,
the proposed S2D-GAN estimates the coarse level depthmap

Paper Details

Authors:
Praful Hambarde, Akshay Dudhane, Prashant W. Patil, Subrahmanyam Murala and Abhinav Dhall
Submitted On:
2 November 2020 - 11:42am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Virtual_PPT_ICIP20.pdf

(8)

Subscribe

[1] Praful Hambarde, Akshay Dudhane, Prashant W. Patil, Subrahmanyam Murala and Abhinav Dhall, "DEPTH ESTIMATION FROM SINGLE IMAGE AND SEMANTIC PRIOR", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5473. Accessed: Nov. 29, 2020.
@article{5473-20,
url = {http://sigport.org/5473},
author = {Praful Hambarde; Akshay Dudhane; Prashant W. Patil; Subrahmanyam Murala and Abhinav Dhall },
publisher = {IEEE SigPort},
title = {DEPTH ESTIMATION FROM SINGLE IMAGE AND SEMANTIC PRIOR},
year = {2020} }
TY - EJOUR
T1 - DEPTH ESTIMATION FROM SINGLE IMAGE AND SEMANTIC PRIOR
AU - Praful Hambarde; Akshay Dudhane; Prashant W. Patil; Subrahmanyam Murala and Abhinav Dhall
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5473
ER -
Praful Hambarde, Akshay Dudhane, Prashant W. Patil, Subrahmanyam Murala and Abhinav Dhall. (2020). DEPTH ESTIMATION FROM SINGLE IMAGE AND SEMANTIC PRIOR. IEEE SigPort. http://sigport.org/5473
Praful Hambarde, Akshay Dudhane, Prashant W. Patil, Subrahmanyam Murala and Abhinav Dhall, 2020. DEPTH ESTIMATION FROM SINGLE IMAGE AND SEMANTIC PRIOR. Available at: http://sigport.org/5473.
Praful Hambarde, Akshay Dudhane, Prashant W. Patil, Subrahmanyam Murala and Abhinav Dhall. (2020). "DEPTH ESTIMATION FROM SINGLE IMAGE AND SEMANTIC PRIOR." Web.
1. Praful Hambarde, Akshay Dudhane, Prashant W. Patil, Subrahmanyam Murala and Abhinav Dhall. DEPTH ESTIMATION FROM SINGLE IMAGE AND SEMANTIC PRIOR [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5473

Summarizing the performances of a background subtraction algorithm measured on several videos


There exist many background subtraction algorithms to detect motion in videos. To help comparing them, datasets with ground-truth data such as CDNET or LASIESTA have been proposed. These datasets organize videos in categories that represent typical challenges for background subtraction. The evaluation procedure promoted by their authors consists in measuring performance indicators for each video separately and to average them hierarchically, within a category first, then between categories, a procedure which we name “summarization”.

Paper Details

Authors:
Sébastien Piérard
Submitted On:
2 November 2020 - 11:37am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Slides of the presentation

(8)

Subscribe

[1] Sébastien Piérard, "Summarizing the performances of a background subtraction algorithm measured on several videos", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5472. Accessed: Nov. 29, 2020.
@article{5472-20,
url = {http://sigport.org/5472},
author = {Sébastien Piérard },
publisher = {IEEE SigPort},
title = {Summarizing the performances of a background subtraction algorithm measured on several videos},
year = {2020} }
TY - EJOUR
T1 - Summarizing the performances of a background subtraction algorithm measured on several videos
AU - Sébastien Piérard
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5472
ER -
Sébastien Piérard. (2020). Summarizing the performances of a background subtraction algorithm measured on several videos. IEEE SigPort. http://sigport.org/5472
Sébastien Piérard, 2020. Summarizing the performances of a background subtraction algorithm measured on several videos. Available at: http://sigport.org/5472.
Sébastien Piérard. (2020). "Summarizing the performances of a background subtraction algorithm measured on several videos." Web.
1. Sébastien Piérard. Summarizing the performances of a background subtraction algorithm measured on several videos [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5472

Cross-Modal Deep Networks For Document Image Classification


As a fundamental step of document related tasks, document classification has been widely adopted to various document image processing applications. Unlike the general image classification problem in the computer vision field, text document images contain both the visual cues and the corresponding text within the image. However, how to bridge these two different modalities and leverage textual and visual features to classify text document images remains challenging.

Paper Details

Authors:
Souhail Bakkali, Zuheng Ming, Mickaël Coustaty, Marçal Rusiñol
Submitted On:
2 November 2020 - 11:26am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2374.pdf

(8)

Keywords

Additional Categories

Subscribe

[1] Souhail Bakkali, Zuheng Ming, Mickaël Coustaty, Marçal Rusiñol, "Cross-Modal Deep Networks For Document Image Classification", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5471. Accessed: Nov. 29, 2020.
@article{5471-20,
url = {http://sigport.org/5471},
author = {Souhail Bakkali; Zuheng Ming; Mickaël Coustaty; Marçal Rusiñol },
publisher = {IEEE SigPort},
title = {Cross-Modal Deep Networks For Document Image Classification},
year = {2020} }
TY - EJOUR
T1 - Cross-Modal Deep Networks For Document Image Classification
AU - Souhail Bakkali; Zuheng Ming; Mickaël Coustaty; Marçal Rusiñol
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5471
ER -
Souhail Bakkali, Zuheng Ming, Mickaël Coustaty, Marçal Rusiñol. (2020). Cross-Modal Deep Networks For Document Image Classification. IEEE SigPort. http://sigport.org/5471
Souhail Bakkali, Zuheng Ming, Mickaël Coustaty, Marçal Rusiñol, 2020. Cross-Modal Deep Networks For Document Image Classification. Available at: http://sigport.org/5471.
Souhail Bakkali, Zuheng Ming, Mickaël Coustaty, Marçal Rusiñol. (2020). "Cross-Modal Deep Networks For Document Image Classification." Web.
1. Souhail Bakkali, Zuheng Ming, Mickaël Coustaty, Marçal Rusiñol. Cross-Modal Deep Networks For Document Image Classification [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5471

ENHANCED IMAGE RECONSTRUCTION FROM QUARTER SAMPLING MEASUREMENTS USING AN ADAPTED VERY DEEP SUPER RESOLUTION NETWORK

Paper Details

Authors:
Submitted On:
2 November 2020 - 11:16am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP2020_Enhanced image reconstruction.pptx

(10)

Subscribe

[1] , "ENHANCED IMAGE RECONSTRUCTION FROM QUARTER SAMPLING MEASUREMENTS USING AN ADAPTED VERY DEEP SUPER RESOLUTION NETWORK", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5470. Accessed: Nov. 29, 2020.
@article{5470-20,
url = {http://sigport.org/5470},
author = { },
publisher = {IEEE SigPort},
title = {ENHANCED IMAGE RECONSTRUCTION FROM QUARTER SAMPLING MEASUREMENTS USING AN ADAPTED VERY DEEP SUPER RESOLUTION NETWORK},
year = {2020} }
TY - EJOUR
T1 - ENHANCED IMAGE RECONSTRUCTION FROM QUARTER SAMPLING MEASUREMENTS USING AN ADAPTED VERY DEEP SUPER RESOLUTION NETWORK
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5470
ER -
. (2020). ENHANCED IMAGE RECONSTRUCTION FROM QUARTER SAMPLING MEASUREMENTS USING AN ADAPTED VERY DEEP SUPER RESOLUTION NETWORK. IEEE SigPort. http://sigport.org/5470
, 2020. ENHANCED IMAGE RECONSTRUCTION FROM QUARTER SAMPLING MEASUREMENTS USING AN ADAPTED VERY DEEP SUPER RESOLUTION NETWORK. Available at: http://sigport.org/5470.
. (2020). "ENHANCED IMAGE RECONSTRUCTION FROM QUARTER SAMPLING MEASUREMENTS USING AN ADAPTED VERY DEEP SUPER RESOLUTION NETWORK." Web.
1. . ENHANCED IMAGE RECONSTRUCTION FROM QUARTER SAMPLING MEASUREMENTS USING AN ADAPTED VERY DEEP SUPER RESOLUTION NETWORK [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5470

Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset


Recently, there has been a growing interest in wearable sensors which provides new research perspectives for 360 ° video analysis. However, the lack of 360 ° datasets in literature hinders the research in this field. To bridge this gap, in this paper we propose a novel Egocentric (first-person) 360° Kinetic human activity video dataset (EgoK360). The EgoK360 dataset contains annotations of human activity with different sub-actions, e.g., activity Ping-Pong with four sub-actions which are pickup-ball, hit, bounce-ball and serve.

Paper Details

Authors:
Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan
Submitted On:
2 November 2020 - 10:59am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip_presentation.pdf

(289)

Subscribe

[1] Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan, "Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5469. Accessed: Nov. 29, 2020.
@article{5469-20,
url = {http://sigport.org/5469},
author = {Mario A. DeLaGarza; Ziliang Zong; Hugo Latapie; Yan Yan },
publisher = {IEEE SigPort},
title = {Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset},
year = {2020} }
TY - EJOUR
T1 - Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset
AU - Mario A. DeLaGarza; Ziliang Zong; Hugo Latapie; Yan Yan
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5469
ER -
Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan. (2020). Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset. IEEE SigPort. http://sigport.org/5469
Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan, 2020. Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset. Available at: http://sigport.org/5469.
Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan. (2020). "Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset." Web.
1. Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan. Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5469

Deep-URL


The lack of interpretability in current deep learning models causes serious concerns as they are extensively used for various life-critical applications. Hence, it is of paramount importance to develop interpretable deep learning models. In this paper, we consider the problem of blind deconvolution and propose a novel model-aware deep architecture that allows for the recovery of both the blur kernel and the sharp image from the blurred image.

Paper Details

Authors:
Shahin Khobahi; Arindam Bose; Mojtaba Soltanalian; Dan Schonfeld
Submitted On:
2 November 2020 - 10:54am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

The final presentation for the video presented at ICIP 2020

(13)

Subscribe

[1] Shahin Khobahi; Arindam Bose; Mojtaba Soltanalian; Dan Schonfeld, "Deep-URL", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5468. Accessed: Nov. 29, 2020.
@article{5468-20,
url = {http://sigport.org/5468},
author = {Shahin Khobahi; Arindam Bose; Mojtaba Soltanalian; Dan Schonfeld },
publisher = {IEEE SigPort},
title = {Deep-URL},
year = {2020} }
TY - EJOUR
T1 - Deep-URL
AU - Shahin Khobahi; Arindam Bose; Mojtaba Soltanalian; Dan Schonfeld
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5468
ER -
Shahin Khobahi; Arindam Bose; Mojtaba Soltanalian; Dan Schonfeld. (2020). Deep-URL. IEEE SigPort. http://sigport.org/5468
Shahin Khobahi; Arindam Bose; Mojtaba Soltanalian; Dan Schonfeld, 2020. Deep-URL. Available at: http://sigport.org/5468.
Shahin Khobahi; Arindam Bose; Mojtaba Soltanalian; Dan Schonfeld. (2020). "Deep-URL." Web.
1. Shahin Khobahi; Arindam Bose; Mojtaba Soltanalian; Dan Schonfeld. Deep-URL [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5468

Attention Boosted Deep Networks for Video Classficaition


Video classification can be performed by summarizing image contents of individual frames into one class by deep neural networks, e.g., CNN and LSTM. Human interpretation of video content is influenced by the attention mechanism. In other words, video class can be more attentively decided by certain information than others. In this paper, we propose to integrate the attention mechanism into deep networks for video classification.

Paper Details

Authors:
Junyong You, Jari Korhonen
Submitted On:
2 November 2020 - 10:39am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Attention Boosted Deep Networks for Video Classficaition.pdf

(11)

Subscribe

[1] Junyong You, Jari Korhonen, "Attention Boosted Deep Networks for Video Classficaition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5467. Accessed: Nov. 29, 2020.
@article{5467-20,
url = {http://sigport.org/5467},
author = {Junyong You; Jari Korhonen },
publisher = {IEEE SigPort},
title = {Attention Boosted Deep Networks for Video Classficaition},
year = {2020} }
TY - EJOUR
T1 - Attention Boosted Deep Networks for Video Classficaition
AU - Junyong You; Jari Korhonen
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5467
ER -
Junyong You, Jari Korhonen. (2020). Attention Boosted Deep Networks for Video Classficaition. IEEE SigPort. http://sigport.org/5467
Junyong You, Jari Korhonen, 2020. Attention Boosted Deep Networks for Video Classficaition. Available at: http://sigport.org/5467.
Junyong You, Jari Korhonen. (2020). "Attention Boosted Deep Networks for Video Classficaition." Web.
1. Junyong You, Jari Korhonen. Attention Boosted Deep Networks for Video Classficaition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5467

Pages