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

Image/Video Processing

Quaternion Harris for Multispectral Keypoint Detection

Paper Details

Authors:
Submitted On:
16 November 2020 - 2:02pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Sfikas ICIP 2020 Quaternion Harris presentation.pdf

(8)

Subscribe

[1] , "Quaternion Harris for Multispectral Keypoint Detection", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5555. Accessed: Dec. 02, 2020.
@article{5555-20,
url = {http://sigport.org/5555},
author = { },
publisher = {IEEE SigPort},
title = {Quaternion Harris for Multispectral Keypoint Detection},
year = {2020} }
TY - EJOUR
T1 - Quaternion Harris for Multispectral Keypoint Detection
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5555
ER -
. (2020). Quaternion Harris for Multispectral Keypoint Detection. IEEE SigPort. http://sigport.org/5555
, 2020. Quaternion Harris for Multispectral Keypoint Detection. Available at: http://sigport.org/5555.
. (2020). "Quaternion Harris for Multispectral Keypoint Detection." Web.
1. . Quaternion Harris for Multispectral Keypoint Detection [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5555

Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data


Segmentation of unseen industrial parts is essential for autonomous industrial systems. However, industrial components are texture-less, reflective, and often found in cluttered and unstructured environments with heavy occlusion, which makes it more challenging to deal with unseen objects. To tackle this problem, we present a synthetic data generation pipeline that randomizes textures via domain randomization to focus on the shape information.

Paper Details

Authors:
Jongwon Kim, Raeyoung Kang, Seungjun Choi, Kyoobin Lee
Submitted On:
15 November 2020 - 3:24am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

PresentationSlides-ICIP2020-Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data.pdf

(9)

Subscribe

[1] Jongwon Kim, Raeyoung Kang, Seungjun Choi, Kyoobin Lee, "Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5554. Accessed: Dec. 02, 2020.
@article{5554-20,
url = {http://sigport.org/5554},
author = {Jongwon Kim; Raeyoung Kang; Seungjun Choi; Kyoobin Lee },
publisher = {IEEE SigPort},
title = {Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data},
year = {2020} }
TY - EJOUR
T1 - Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data
AU - Jongwon Kim; Raeyoung Kang; Seungjun Choi; Kyoobin Lee
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5554
ER -
Jongwon Kim, Raeyoung Kang, Seungjun Choi, Kyoobin Lee. (2020). Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data. IEEE SigPort. http://sigport.org/5554
Jongwon Kim, Raeyoung Kang, Seungjun Choi, Kyoobin Lee, 2020. Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data. Available at: http://sigport.org/5554.
Jongwon Kim, Raeyoung Kang, Seungjun Choi, Kyoobin Lee. (2020). "Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data." Web.
1. Jongwon Kim, Raeyoung Kang, Seungjun Choi, Kyoobin Lee. Segmenting Unseen Industrial Components In A Heavy Clutter Using RGB-D Fusion And Synthetic Data [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5554

DOES SUPER-RESOLUTION IMPROVE OCR PERFORMANCE IN THE REAL WORLD? A CASE STUDY ON IMAGES OF RECEIPTS


Recently, many deep learning methods have been used to handle single image super-resolution (SISR) tasks and often achieve state-of-the-art performance. From a visual point of view, the results look convincing. Yet, does it mean that those techniques are reliable and robust enough to be implemented in real business cases to enhance the performance of other computer vision tasks?

Paper Details

Authors:
Vivien Robert, Hugues Talbot
Submitted On:
13 November 2020 - 12:52pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP Thesis Presentation.pdf

(13)

Subscribe

[1] Vivien Robert, Hugues Talbot, "DOES SUPER-RESOLUTION IMPROVE OCR PERFORMANCE IN THE REAL WORLD? A CASE STUDY ON IMAGES OF RECEIPTS", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5553. Accessed: Dec. 02, 2020.
@article{5553-20,
url = {http://sigport.org/5553},
author = {Vivien Robert; Hugues Talbot },
publisher = {IEEE SigPort},
title = {DOES SUPER-RESOLUTION IMPROVE OCR PERFORMANCE IN THE REAL WORLD? A CASE STUDY ON IMAGES OF RECEIPTS},
year = {2020} }
TY - EJOUR
T1 - DOES SUPER-RESOLUTION IMPROVE OCR PERFORMANCE IN THE REAL WORLD? A CASE STUDY ON IMAGES OF RECEIPTS
AU - Vivien Robert; Hugues Talbot
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5553
ER -
Vivien Robert, Hugues Talbot. (2020). DOES SUPER-RESOLUTION IMPROVE OCR PERFORMANCE IN THE REAL WORLD? A CASE STUDY ON IMAGES OF RECEIPTS. IEEE SigPort. http://sigport.org/5553
Vivien Robert, Hugues Talbot, 2020. DOES SUPER-RESOLUTION IMPROVE OCR PERFORMANCE IN THE REAL WORLD? A CASE STUDY ON IMAGES OF RECEIPTS. Available at: http://sigport.org/5553.
Vivien Robert, Hugues Talbot. (2020). "DOES SUPER-RESOLUTION IMPROVE OCR PERFORMANCE IN THE REAL WORLD? A CASE STUDY ON IMAGES OF RECEIPTS." Web.
1. Vivien Robert, Hugues Talbot. DOES SUPER-RESOLUTION IMPROVE OCR PERFORMANCE IN THE REAL WORLD? A CASE STUDY ON IMAGES OF RECEIPTS [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5553

Improving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GAN


Face detection and recognition in the wild is currently one of the most interesting and challenging problems. Many algorithms with high performance have already been proposed and applied in real-world applications. However, the problem of detecting and recognising degraded faces from low-quality images and videos mostly remains unsolved. In this paper, we present an algorithm capable of recovering facial features from low-quality videos and images. The resulting output image boosts the performance of existing face detection and recognition algorithms.

Paper Details

Authors:
Soumya Shubhra Ghosh, Yang Hua, Sankha Subhra Mukherjee, Neil Robertson
Submitted On:
9 November 2020 - 5:21pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_2020_slides.pdf

(12)

Subscribe

[1] Soumya Shubhra Ghosh, Yang Hua, Sankha Subhra Mukherjee, Neil Robertson, "Improving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GAN", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5550. Accessed: Dec. 02, 2020.
@article{5550-20,
url = {http://sigport.org/5550},
author = {Soumya Shubhra Ghosh; Yang Hua; Sankha Subhra Mukherjee; Neil Robertson },
publisher = {IEEE SigPort},
title = {Improving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GAN},
year = {2020} }
TY - EJOUR
T1 - Improving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GAN
AU - Soumya Shubhra Ghosh; Yang Hua; Sankha Subhra Mukherjee; Neil Robertson
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5550
ER -
Soumya Shubhra Ghosh, Yang Hua, Sankha Subhra Mukherjee, Neil Robertson. (2020). Improving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GAN. IEEE SigPort. http://sigport.org/5550
Soumya Shubhra Ghosh, Yang Hua, Sankha Subhra Mukherjee, Neil Robertson, 2020. Improving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GAN. Available at: http://sigport.org/5550.
Soumya Shubhra Ghosh, Yang Hua, Sankha Subhra Mukherjee, Neil Robertson. (2020). "Improving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GAN." Web.
1. Soumya Shubhra Ghosh, Yang Hua, Sankha Subhra Mukherjee, Neil Robertson. Improving Detection and Recognition of Degraded Faces by Discriminative Feature Restoration Using GAN [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5550

FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network

Paper Details

Authors:
Jie Yang
Submitted On:
5 November 2020 - 9:00am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

FDFlowNet.pdf

(10)

Subscribe

[1] Jie Yang, "FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5543. Accessed: Dec. 02, 2020.
@article{5543-20,
url = {http://sigport.org/5543},
author = {Jie Yang },
publisher = {IEEE SigPort},
title = {FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network},
year = {2020} }
TY - EJOUR
T1 - FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network
AU - Jie Yang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5543
ER -
Jie Yang. (2020). FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network. IEEE SigPort. http://sigport.org/5543
Jie Yang, 2020. FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network. Available at: http://sigport.org/5543.
Jie Yang. (2020). "FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network." Web.
1. Jie Yang. FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5543

Pose Guided Person Image Generation Based on Pose Skeleton Sequence and 3D Convolution

Paper Details

Authors:
Submitted On:
5 November 2020 - 4:54am
Short Link:
Type:
Event:

Document Files

presentation.pptx

(12)

Subscribe

[1] , "Pose Guided Person Image Generation Based on Pose Skeleton Sequence and 3D Convolution", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5540. Accessed: Dec. 02, 2020.
@article{5540-20,
url = {http://sigport.org/5540},
author = { },
publisher = {IEEE SigPort},
title = {Pose Guided Person Image Generation Based on Pose Skeleton Sequence and 3D Convolution},
year = {2020} }
TY - EJOUR
T1 - Pose Guided Person Image Generation Based on Pose Skeleton Sequence and 3D Convolution
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5540
ER -
. (2020). Pose Guided Person Image Generation Based on Pose Skeleton Sequence and 3D Convolution. IEEE SigPort. http://sigport.org/5540
, 2020. Pose Guided Person Image Generation Based on Pose Skeleton Sequence and 3D Convolution. Available at: http://sigport.org/5540.
. (2020). "Pose Guided Person Image Generation Based on Pose Skeleton Sequence and 3D Convolution." Web.
1. . Pose Guided Person Image Generation Based on Pose Skeleton Sequence and 3D Convolution [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5540

Sparsity preserved canonical correlation analysis


Canonical correlation analysis (CCA) describes the relationship between two sets of variables by finding linear combinations of the variables with maximal correlation. Recently, under the assumption that the leading canonical correlation directions are sparse, various procedures have been proposed for many high-dimensional applications to improve the interpretability of CCA. However all these procedures have the inconvenience of not preserving the sparsity among the retained leading canonical directions. To address this issue, a new sparse CCA method is proposed in this paper.

Paper Details

Authors:
Abd-Krim Seghouane, Muhammad Ali Qadar
Submitted On:
5 November 2020 - 3:01am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP 2020 talk

(8)

Subscribe

[1] Abd-Krim Seghouane, Muhammad Ali Qadar, "Sparsity preserved canonical correlation analysis", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5538. Accessed: Dec. 02, 2020.
@article{5538-20,
url = {http://sigport.org/5538},
author = {Abd-Krim Seghouane; Muhammad Ali Qadar },
publisher = {IEEE SigPort},
title = {Sparsity preserved canonical correlation analysis},
year = {2020} }
TY - EJOUR
T1 - Sparsity preserved canonical correlation analysis
AU - Abd-Krim Seghouane; Muhammad Ali Qadar
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5538
ER -
Abd-Krim Seghouane, Muhammad Ali Qadar. (2020). Sparsity preserved canonical correlation analysis. IEEE SigPort. http://sigport.org/5538
Abd-Krim Seghouane, Muhammad Ali Qadar, 2020. Sparsity preserved canonical correlation analysis. Available at: http://sigport.org/5538.
Abd-Krim Seghouane, Muhammad Ali Qadar. (2020). "Sparsity preserved canonical correlation analysis." Web.
1. Abd-Krim Seghouane, Muhammad Ali Qadar. Sparsity preserved canonical correlation analysis [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5538

ICIP 2020 Paper #2783: FEW SHOT LEARNING FOR POINT CLOUD DATA USING MODEL AGNOSTIC META LEARNING


The ability of deep neural networks to extract complex statistics and learn high level features from vast datasets is proven.Yet current deep learning approaches suffer from poor sample efficiency in stark contrast to human perception. Fewshot learning algorithms such as matching networks or ModelAgnostic Meta Learning (MAML) mitigate this problem, enabling fast learning with few examples. In this paper, we ex-tend the MAML algorithm to point cloud data using a Point-Net Architecture.

Paper Details

Authors:
Rishi Puri, Avideh Zakhor, Raul Puri
Submitted On:
4 November 2020 - 10:59am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Icip_2019_Maml_for_pointclouds_Final (1).pdf

(9)

Subscribe

[1] Rishi Puri, Avideh Zakhor, Raul Puri, "ICIP 2020 Paper #2783: FEW SHOT LEARNING FOR POINT CLOUD DATA USING MODEL AGNOSTIC META LEARNING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5535. Accessed: Dec. 02, 2020.
@article{5535-20,
url = {http://sigport.org/5535},
author = {Rishi Puri; Avideh Zakhor; Raul Puri },
publisher = {IEEE SigPort},
title = {ICIP 2020 Paper #2783: FEW SHOT LEARNING FOR POINT CLOUD DATA USING MODEL AGNOSTIC META LEARNING},
year = {2020} }
TY - EJOUR
T1 - ICIP 2020 Paper #2783: FEW SHOT LEARNING FOR POINT CLOUD DATA USING MODEL AGNOSTIC META LEARNING
AU - Rishi Puri; Avideh Zakhor; Raul Puri
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5535
ER -
Rishi Puri, Avideh Zakhor, Raul Puri. (2020). ICIP 2020 Paper #2783: FEW SHOT LEARNING FOR POINT CLOUD DATA USING MODEL AGNOSTIC META LEARNING. IEEE SigPort. http://sigport.org/5535
Rishi Puri, Avideh Zakhor, Raul Puri, 2020. ICIP 2020 Paper #2783: FEW SHOT LEARNING FOR POINT CLOUD DATA USING MODEL AGNOSTIC META LEARNING. Available at: http://sigport.org/5535.
Rishi Puri, Avideh Zakhor, Raul Puri. (2020). "ICIP 2020 Paper #2783: FEW SHOT LEARNING FOR POINT CLOUD DATA USING MODEL AGNOSTIC META LEARNING." Web.
1. Rishi Puri, Avideh Zakhor, Raul Puri. ICIP 2020 Paper #2783: FEW SHOT LEARNING FOR POINT CLOUD DATA USING MODEL AGNOSTIC META LEARNING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5535

Development of New Fractal and Non-fractal Deep Residual Networks for Deblocking of JPEG Decompressed Images

Paper Details

Authors:
Alireza Esmaeilzehi, M. Omair Ahmad, M.N.S. Swamy
Submitted On:
4 November 2020 - 8:45am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Slides

(7)

Subscribe

[1] Alireza Esmaeilzehi, M. Omair Ahmad, M.N.S. Swamy, "Development of New Fractal and Non-fractal Deep Residual Networks for Deblocking of JPEG Decompressed Images", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5533. Accessed: Dec. 02, 2020.
@article{5533-20,
url = {http://sigport.org/5533},
author = {Alireza Esmaeilzehi; M. Omair Ahmad; M.N.S. Swamy },
publisher = {IEEE SigPort},
title = {Development of New Fractal and Non-fractal Deep Residual Networks for Deblocking of JPEG Decompressed Images},
year = {2020} }
TY - EJOUR
T1 - Development of New Fractal and Non-fractal Deep Residual Networks for Deblocking of JPEG Decompressed Images
AU - Alireza Esmaeilzehi; M. Omair Ahmad; M.N.S. Swamy
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5533
ER -
Alireza Esmaeilzehi, M. Omair Ahmad, M.N.S. Swamy. (2020). Development of New Fractal and Non-fractal Deep Residual Networks for Deblocking of JPEG Decompressed Images. IEEE SigPort. http://sigport.org/5533
Alireza Esmaeilzehi, M. Omair Ahmad, M.N.S. Swamy, 2020. Development of New Fractal and Non-fractal Deep Residual Networks for Deblocking of JPEG Decompressed Images. Available at: http://sigport.org/5533.
Alireza Esmaeilzehi, M. Omair Ahmad, M.N.S. Swamy. (2020). "Development of New Fractal and Non-fractal Deep Residual Networks for Deblocking of JPEG Decompressed Images." Web.
1. Alireza Esmaeilzehi, M. Omair Ahmad, M.N.S. Swamy. Development of New Fractal and Non-fractal Deep Residual Networks for Deblocking of JPEG Decompressed Images [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5533

ICIP2020-Slides


Motions of facial components convey significant information of facial expressions. Although remarkable advancement has been made, the dynamic of facial topology has not been fully exploited. In this paper, a novel facial expression recognition (FER) algorithm called Spatial Temporal Semantic Graph Network (STSGN) is proposed to automatically learn spatial and temporal patterns through end-to-end feature learning from facial topology structure.

Paper Details

Authors:
Submitted On:
3 November 2020 - 11:21pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

The slides of my ICIP presentation for the paper FACIAL EXPRESSION RECOGNITION USING SPATIAL-TEMPORAL SEMANTIC GRAPH NETWORK

(8)

Subscribe

[1] , "ICIP2020-Slides", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5529. Accessed: Dec. 02, 2020.
@article{5529-20,
url = {http://sigport.org/5529},
author = { },
publisher = {IEEE SigPort},
title = {ICIP2020-Slides},
year = {2020} }
TY - EJOUR
T1 - ICIP2020-Slides
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5529
ER -
. (2020). ICIP2020-Slides. IEEE SigPort. http://sigport.org/5529
, 2020. ICIP2020-Slides. Available at: http://sigport.org/5529.
. (2020). "ICIP2020-Slides." Web.
1. . ICIP2020-Slides [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5529

Pages