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

LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION

Paper Details

Authors:
Yan Li, Xiaoyi Chen, Li Quan, Ni Zhang
Submitted On:
5 November 2020 - 12:51am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

pres_v0.0.1.8_20200820_fin2.pdf

(8)

Subscribe

[1] Yan Li, Xiaoyi Chen, Li Quan, Ni Zhang, "LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5537. Accessed: Nov. 26, 2020.
@article{5537-20,
url = {http://sigport.org/5537},
author = {Yan Li; Xiaoyi Chen; Li Quan; Ni Zhang },
publisher = {IEEE SigPort},
title = {LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION},
year = {2020} }
TY - EJOUR
T1 - LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION
AU - Yan Li; Xiaoyi Chen; Li Quan; Ni Zhang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5537
ER -
Yan Li, Xiaoyi Chen, Li Quan, Ni Zhang. (2020). LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION. IEEE SigPort. http://sigport.org/5537
Yan Li, Xiaoyi Chen, Li Quan, Ni Zhang, 2020. LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION. Available at: http://sigport.org/5537.
Yan Li, Xiaoyi Chen, Li Quan, Ni Zhang. (2020). "LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION." Web.
1. Yan Li, Xiaoyi Chen, Li Quan, Ni Zhang. LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5537

DEEP SMOOTHED PROJECTED LANDWEBER NETWORK FOR BLOCK-BASED IMAGE COMPRESSIVE SENSING

Paper Details

Authors:
Submitted On:
4 November 2020 - 11:08am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP_presentation.pdf

(246)

Subscribe

[1] , "DEEP SMOOTHED PROJECTED LANDWEBER NETWORK FOR BLOCK-BASED IMAGE COMPRESSIVE SENSING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5536. Accessed: Nov. 26, 2020.
@article{5536-20,
url = {http://sigport.org/5536},
author = { },
publisher = {IEEE SigPort},
title = {DEEP SMOOTHED PROJECTED LANDWEBER NETWORK FOR BLOCK-BASED IMAGE COMPRESSIVE SENSING},
year = {2020} }
TY - EJOUR
T1 - DEEP SMOOTHED PROJECTED LANDWEBER NETWORK FOR BLOCK-BASED IMAGE COMPRESSIVE SENSING
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5536
ER -
. (2020). DEEP SMOOTHED PROJECTED LANDWEBER NETWORK FOR BLOCK-BASED IMAGE COMPRESSIVE SENSING. IEEE SigPort. http://sigport.org/5536
, 2020. DEEP SMOOTHED PROJECTED LANDWEBER NETWORK FOR BLOCK-BASED IMAGE COMPRESSIVE SENSING. Available at: http://sigport.org/5536.
. (2020). "DEEP SMOOTHED PROJECTED LANDWEBER NETWORK FOR BLOCK-BASED IMAGE COMPRESSIVE SENSING." Web.
1. . DEEP SMOOTHED PROJECTED LANDWEBER NETWORK FOR BLOCK-BASED IMAGE COMPRESSIVE SENSING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5536

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

(8)

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: Nov. 26, 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

Motion Blur Prior


Priors play an important role of regularizers in image deblurring algorithms. Image priors are frequently studied and many forms were proposed in the literature. Blur priors are considered less important and the most common forms are simple uniform distributions with domain constraints. We propose a more informative blur prior based on the notion of atomic norm which favors blurs composed of line segments and is suitable for motion blur. The prior is formulated as a linear program that can be inserted into any optimization task.

Paper Details

Authors:
F. Sroubek, J. Kotera
Submitted On:
4 November 2020 - 9:07am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP2020_prior.pdf

(9)

Subscribe

[1] F. Sroubek, J. Kotera, "Motion Blur Prior", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5534. Accessed: Nov. 26, 2020.
@article{5534-20,
url = {http://sigport.org/5534},
author = {F. Sroubek; J. Kotera },
publisher = {IEEE SigPort},
title = {Motion Blur Prior},
year = {2020} }
TY - EJOUR
T1 - Motion Blur Prior
AU - F. Sroubek; J. Kotera
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5534
ER -
F. Sroubek, J. Kotera. (2020). Motion Blur Prior. IEEE SigPort. http://sigport.org/5534
F. Sroubek, J. Kotera, 2020. Motion Blur Prior. Available at: http://sigport.org/5534.
F. Sroubek, J. Kotera. (2020). "Motion Blur Prior." Web.
1. F. Sroubek, J. Kotera. Motion Blur Prior [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5534

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

(6)

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: Nov. 26, 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

Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-based Two-Person Interaction Recognition


Spatial-temporal graph convolutional networks (ST-GCN) have achieved outstanding performances on human action recognition, however, it might be less superior on a two-person interaction recognition (TPIR) task due to the relationship of each skeleton is not considered. In this study, we present an improvement of the ST-GCN model that focused on TPIR by employing the pairwise adjacency matrix to capture the relationship of person-person skeletons (ST-GCN-PAM). To validate the effectiveness of the proposed ST-GCN-PAM model on TPIR, experiments were conducted on NTU RGB+D 120.

Paper Details

Authors:
Chao-Lung Yang, Aji Setyoko, Hendrik Tampubolon, Kai-Lung Hua
Submitted On:
4 November 2020 - 5:41am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ST-GCN-PAM[ICIP][Slides].pdf

(13)

Subscribe

[1] Chao-Lung Yang, Aji Setyoko, Hendrik Tampubolon, Kai-Lung Hua, "Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-based Two-Person Interaction Recognition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5532. Accessed: Nov. 26, 2020.
@article{5532-20,
url = {http://sigport.org/5532},
author = {Chao-Lung Yang; Aji Setyoko; Hendrik Tampubolon; Kai-Lung Hua },
publisher = {IEEE SigPort},
title = {Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-based Two-Person Interaction Recognition},
year = {2020} }
TY - EJOUR
T1 - Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-based Two-Person Interaction Recognition
AU - Chao-Lung Yang; Aji Setyoko; Hendrik Tampubolon; Kai-Lung Hua
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5532
ER -
Chao-Lung Yang, Aji Setyoko, Hendrik Tampubolon, Kai-Lung Hua. (2020). Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-based Two-Person Interaction Recognition. IEEE SigPort. http://sigport.org/5532
Chao-Lung Yang, Aji Setyoko, Hendrik Tampubolon, Kai-Lung Hua, 2020. Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-based Two-Person Interaction Recognition. Available at: http://sigport.org/5532.
Chao-Lung Yang, Aji Setyoko, Hendrik Tampubolon, Kai-Lung Hua. (2020). "Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-based Two-Person Interaction Recognition." Web.
1. Chao-Lung Yang, Aji Setyoko, Hendrik Tampubolon, Kai-Lung Hua. Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-based Two-Person Interaction Recognition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5532

GLAUCOMA DETECTION FROM RAW CIRCUMPAPILLARY OCT IMAGES USING FULLY CONVOLUTIONAL NEURAL NETWORKS

Paper Details

Authors:
Gabriel García, Rocío del Amor, Adrián Colomer, Valery Naranjo
Submitted On:
4 November 2020 - 5:29am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_2020_GG_RA_AC_VN.pptx

(13)

Keywords

Additional Categories

Subscribe

[1] Gabriel García, Rocío del Amor, Adrián Colomer, Valery Naranjo, "GLAUCOMA DETECTION FROM RAW CIRCUMPAPILLARY OCT IMAGES USING FULLY CONVOLUTIONAL NEURAL NETWORKS", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5531. Accessed: Nov. 26, 2020.
@article{5531-20,
url = {http://sigport.org/5531},
author = {Gabriel García; Rocío del Amor; Adrián Colomer; Valery Naranjo },
publisher = {IEEE SigPort},
title = {GLAUCOMA DETECTION FROM RAW CIRCUMPAPILLARY OCT IMAGES USING FULLY CONVOLUTIONAL NEURAL NETWORKS},
year = {2020} }
TY - EJOUR
T1 - GLAUCOMA DETECTION FROM RAW CIRCUMPAPILLARY OCT IMAGES USING FULLY CONVOLUTIONAL NEURAL NETWORKS
AU - Gabriel García; Rocío del Amor; Adrián Colomer; Valery Naranjo
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5531
ER -
Gabriel García, Rocío del Amor, Adrián Colomer, Valery Naranjo. (2020). GLAUCOMA DETECTION FROM RAW CIRCUMPAPILLARY OCT IMAGES USING FULLY CONVOLUTIONAL NEURAL NETWORKS. IEEE SigPort. http://sigport.org/5531
Gabriel García, Rocío del Amor, Adrián Colomer, Valery Naranjo, 2020. GLAUCOMA DETECTION FROM RAW CIRCUMPAPILLARY OCT IMAGES USING FULLY CONVOLUTIONAL NEURAL NETWORKS. Available at: http://sigport.org/5531.
Gabriel García, Rocío del Amor, Adrián Colomer, Valery Naranjo. (2020). "GLAUCOMA DETECTION FROM RAW CIRCUMPAPILLARY OCT IMAGES USING FULLY CONVOLUTIONAL NEURAL NETWORKS." Web.
1. Gabriel García, Rocío del Amor, Adrián Colomer, Valery Naranjo. GLAUCOMA DETECTION FROM RAW CIRCUMPAPILLARY OCT IMAGES USING FULLY CONVOLUTIONAL NEURAL NETWORKS [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5531

RTip : A Fully Automated Root Tip Tracker for Measuring Plant Growth With Intermittent Perturbations


RTip is a tool to quantify plant root growth velocity using high-resolution microscopy image sequences at sub-pixel accuracy. The fully automated RTip tracker is designed for high-throughput analysis of plant phenotyping experiments with episodic perturbations. RTip is able to auto-skip past these manual intervention perturbation activity, i.e. when the root tip is not under the microscope, the image is distorted or blurred. RTip provides the most accurate root growth velocity results with the lowest variance (i.e.

Paper Details

Authors:
Deniz Kavzak Ufuktepe, Kannappan Palaniappan, Melissa Elmali, Tobias I. Baskin
Submitted On:
4 November 2020 - 12:50am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

RTip.pdf

(7)

Subscribe

[1] Deniz Kavzak Ufuktepe, Kannappan Palaniappan, Melissa Elmali, Tobias I. Baskin, "RTip : A Fully Automated Root Tip Tracker for Measuring Plant Growth With Intermittent Perturbations", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5530. Accessed: Nov. 26, 2020.
@article{5530-20,
url = {http://sigport.org/5530},
author = {Deniz Kavzak Ufuktepe; Kannappan Palaniappan; Melissa Elmali; Tobias I. Baskin },
publisher = {IEEE SigPort},
title = {RTip : A Fully Automated Root Tip Tracker for Measuring Plant Growth With Intermittent Perturbations},
year = {2020} }
TY - EJOUR
T1 - RTip : A Fully Automated Root Tip Tracker for Measuring Plant Growth With Intermittent Perturbations
AU - Deniz Kavzak Ufuktepe; Kannappan Palaniappan; Melissa Elmali; Tobias I. Baskin
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5530
ER -
Deniz Kavzak Ufuktepe, Kannappan Palaniappan, Melissa Elmali, Tobias I. Baskin. (2020). RTip : A Fully Automated Root Tip Tracker for Measuring Plant Growth With Intermittent Perturbations. IEEE SigPort. http://sigport.org/5530
Deniz Kavzak Ufuktepe, Kannappan Palaniappan, Melissa Elmali, Tobias I. Baskin, 2020. RTip : A Fully Automated Root Tip Tracker for Measuring Plant Growth With Intermittent Perturbations. Available at: http://sigport.org/5530.
Deniz Kavzak Ufuktepe, Kannappan Palaniappan, Melissa Elmali, Tobias I. Baskin. (2020). "RTip : A Fully Automated Root Tip Tracker for Measuring Plant Growth With Intermittent Perturbations." Web.
1. Deniz Kavzak Ufuktepe, Kannappan Palaniappan, Melissa Elmali, Tobias I. Baskin. RTip : A Fully Automated Root Tip Tracker for Measuring Plant Growth With Intermittent Perturbations [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5530

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: Nov. 26, 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

Activity Normalization for Activity Detection in Surveillance Videos

Paper Details

Authors:
Takashi Hosono,Kiyohito Sawada, Youngqing Sun,Kazuya Hayase,Jun Shimamura
Submitted On:
3 November 2020 - 11:18pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

presentation_r5.pdf

(9)

Keywords

Additional Categories

Subscribe

[1] Takashi Hosono,Kiyohito Sawada, Youngqing Sun,Kazuya Hayase,Jun Shimamura, "Activity Normalization for Activity Detection in Surveillance Videos", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5528. Accessed: Nov. 26, 2020.
@article{5528-20,
url = {http://sigport.org/5528},
author = {Takashi Hosono;Kiyohito Sawada; Youngqing Sun;Kazuya Hayase;Jun Shimamura },
publisher = {IEEE SigPort},
title = {Activity Normalization for Activity Detection in Surveillance Videos},
year = {2020} }
TY - EJOUR
T1 - Activity Normalization for Activity Detection in Surveillance Videos
AU - Takashi Hosono;Kiyohito Sawada; Youngqing Sun;Kazuya Hayase;Jun Shimamura
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5528
ER -
Takashi Hosono,Kiyohito Sawada, Youngqing Sun,Kazuya Hayase,Jun Shimamura. (2020). Activity Normalization for Activity Detection in Surveillance Videos. IEEE SigPort. http://sigport.org/5528
Takashi Hosono,Kiyohito Sawada, Youngqing Sun,Kazuya Hayase,Jun Shimamura, 2020. Activity Normalization for Activity Detection in Surveillance Videos. Available at: http://sigport.org/5528.
Takashi Hosono,Kiyohito Sawada, Youngqing Sun,Kazuya Hayase,Jun Shimamura. (2020). "Activity Normalization for Activity Detection in Surveillance Videos." Web.
1. Takashi Hosono,Kiyohito Sawada, Youngqing Sun,Kazuya Hayase,Jun Shimamura. Activity Normalization for Activity Detection in Surveillance Videos [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5528

Pages