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

Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization

Paper Details

Authors:
Fengbo Lan, Cheng Yang, Gene Cheung, Jack Z. G. Tan
Submitted On:
2 November 2020 - 4:04pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_20_slides.pdf

(5)

Subscribe

[1] Fengbo Lan, Cheng Yang, Gene Cheung, Jack Z. G. Tan, "Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5486. Accessed: Nov. 26, 2020.
@article{5486-20,
url = {http://sigport.org/5486},
author = {Fengbo Lan; Cheng Yang; Gene Cheung; Jack Z. G. Tan },
publisher = {IEEE SigPort},
title = {Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization},
year = {2020} }
TY - EJOUR
T1 - Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization
AU - Fengbo Lan; Cheng Yang; Gene Cheung; Jack Z. G. Tan
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5486
ER -
Fengbo Lan, Cheng Yang, Gene Cheung, Jack Z. G. Tan. (2020). Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization. IEEE SigPort. http://sigport.org/5486
Fengbo Lan, Cheng Yang, Gene Cheung, Jack Z. G. Tan, 2020. Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization. Available at: http://sigport.org/5486.
Fengbo Lan, Cheng Yang, Gene Cheung, Jack Z. G. Tan. (2020). "Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization." Web.
1. Fengbo Lan, Cheng Yang, Gene Cheung, Jack Z. G. Tan. Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5486

Open-Set Metric Learning for Person Re-identification in The Wild


Person re-identification in the wild needs to simultaneously (frame-wise) detect and re-identify persons and has wide utility in practical scenarios. However, such tasks come with an additional open-set re-ID challenge as all probe persons may not necessarily be present in the (frame-wise) dynamic gallery. Traditional or close-set re-ID systems are not equipped to handle such cases and raise several false alarms as a result. To cope with such challenges open-set metric learning (OSML), based on the concept of Large margin nearest neighbor (LMNN) approach, is proposed.

Paper Details

Authors:
Arindam Sikdar, Dibyadip Chatterjee, Arpan Bhowmik, Ananda S. Chowdhury
Submitted On:
2 November 2020 - 3:23pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation Paper 2396.pdf

(7)

Subscribe

[1] Arindam Sikdar, Dibyadip Chatterjee, Arpan Bhowmik, Ananda S. Chowdhury, "Open-Set Metric Learning for Person Re-identification in The Wild", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5485. Accessed: Nov. 26, 2020.
@article{5485-20,
url = {http://sigport.org/5485},
author = {Arindam Sikdar; Dibyadip Chatterjee; Arpan Bhowmik; Ananda S. Chowdhury },
publisher = {IEEE SigPort},
title = {Open-Set Metric Learning for Person Re-identification in The Wild},
year = {2020} }
TY - EJOUR
T1 - Open-Set Metric Learning for Person Re-identification in The Wild
AU - Arindam Sikdar; Dibyadip Chatterjee; Arpan Bhowmik; Ananda S. Chowdhury
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5485
ER -
Arindam Sikdar, Dibyadip Chatterjee, Arpan Bhowmik, Ananda S. Chowdhury. (2020). Open-Set Metric Learning for Person Re-identification in The Wild. IEEE SigPort. http://sigport.org/5485
Arindam Sikdar, Dibyadip Chatterjee, Arpan Bhowmik, Ananda S. Chowdhury, 2020. Open-Set Metric Learning for Person Re-identification in The Wild. Available at: http://sigport.org/5485.
Arindam Sikdar, Dibyadip Chatterjee, Arpan Bhowmik, Ananda S. Chowdhury. (2020). "Open-Set Metric Learning for Person Re-identification in The Wild." Web.
1. Arindam Sikdar, Dibyadip Chatterjee, Arpan Bhowmik, Ananda S. Chowdhury. Open-Set Metric Learning for Person Re-identification in The Wild [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5485

Bubblenet: A Disperse Recurrent Structure To Recognize Activities


This paper presents an approach to perform human activity recognition in videos through the employment of a deep recurrent network, taking as inputs appearance and optical flow information. Our method proposes a novel architecture named BubbleNET, which is based on a recurrent layer dispersed into several modules (referred to as bubbles) along with an attention mechanism based on squeeze-and-excitation strategy, responsible to modulate each bubble contribution.

Paper Details

Authors:
Igor L. O. Bastos, Victor H. C. Melo, William Robson Schwatz
Submitted On:
2 November 2020 - 3:16pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2247.pdf

(8)

Subscribe

[1] Igor L. O. Bastos, Victor H. C. Melo, William Robson Schwatz, "Bubblenet: A Disperse Recurrent Structure To Recognize Activities", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5484. Accessed: Nov. 26, 2020.
@article{5484-20,
url = {http://sigport.org/5484},
author = {Igor L. O. Bastos; Victor H. C. Melo; William Robson Schwatz },
publisher = {IEEE SigPort},
title = {Bubblenet: A Disperse Recurrent Structure To Recognize Activities},
year = {2020} }
TY - EJOUR
T1 - Bubblenet: A Disperse Recurrent Structure To Recognize Activities
AU - Igor L. O. Bastos; Victor H. C. Melo; William Robson Schwatz
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5484
ER -
Igor L. O. Bastos, Victor H. C. Melo, William Robson Schwatz. (2020). Bubblenet: A Disperse Recurrent Structure To Recognize Activities. IEEE SigPort. http://sigport.org/5484
Igor L. O. Bastos, Victor H. C. Melo, William Robson Schwatz, 2020. Bubblenet: A Disperse Recurrent Structure To Recognize Activities. Available at: http://sigport.org/5484.
Igor L. O. Bastos, Victor H. C. Melo, William Robson Schwatz. (2020). "Bubblenet: A Disperse Recurrent Structure To Recognize Activities." Web.
1. Igor L. O. Bastos, Victor H. C. Melo, William Robson Schwatz. Bubblenet: A Disperse Recurrent Structure To Recognize Activities [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5484

PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance


Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was usually taken from the human visual perceptual system and how the system processes different perturbations in order to replicate to what extent it determines our ability to judge image quality. While recent works have presented deep neural networks trained to predict human perceptual quality, very few borrow any intuitions from the human visual system.

Paper Details

Authors:
Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez
Submitted On:
2 November 2020 - 2:26pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP_2020_presentation.pdf

(9)

Subscribe

[1] Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez, "PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5483. Accessed: Nov. 26, 2020.
@article{5483-20,
url = {http://sigport.org/5483},
author = {Valero Laparra; Jesus Malo; Ryan McConville; Raul Santos-Rodriguez },
publisher = {IEEE SigPort},
title = {PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance},
year = {2020} }
TY - EJOUR
T1 - PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance
AU - Valero Laparra; Jesus Malo; Ryan McConville; Raul Santos-Rodriguez
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5483
ER -
Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez. (2020). PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance. IEEE SigPort. http://sigport.org/5483
Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez, 2020. PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance. Available at: http://sigport.org/5483.
Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez. (2020). "PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance." Web.
1. Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez. PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5483

DEPTH MAPS FAST SCALABLE COMPRESSION BASED ON CODING UNIT DEPTH

Paper Details

Authors:
Sonia Mosbah, Dorsaf Sebai, Faouzi Ghorbel
Submitted On:
2 November 2020 - 2:27pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Présentation_Dorsaf Sebai.pdf

(9)

Subscribe

[1] Sonia Mosbah, Dorsaf Sebai, Faouzi Ghorbel, "DEPTH MAPS FAST SCALABLE COMPRESSION BASED ON CODING UNIT DEPTH", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5482. Accessed: Nov. 26, 2020.
@article{5482-20,
url = {http://sigport.org/5482},
author = {Sonia Mosbah; Dorsaf Sebai; Faouzi Ghorbel },
publisher = {IEEE SigPort},
title = {DEPTH MAPS FAST SCALABLE COMPRESSION BASED ON CODING UNIT DEPTH},
year = {2020} }
TY - EJOUR
T1 - DEPTH MAPS FAST SCALABLE COMPRESSION BASED ON CODING UNIT DEPTH
AU - Sonia Mosbah; Dorsaf Sebai; Faouzi Ghorbel
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5482
ER -
Sonia Mosbah, Dorsaf Sebai, Faouzi Ghorbel. (2020). DEPTH MAPS FAST SCALABLE COMPRESSION BASED ON CODING UNIT DEPTH. IEEE SigPort. http://sigport.org/5482
Sonia Mosbah, Dorsaf Sebai, Faouzi Ghorbel, 2020. DEPTH MAPS FAST SCALABLE COMPRESSION BASED ON CODING UNIT DEPTH. Available at: http://sigport.org/5482.
Sonia Mosbah, Dorsaf Sebai, Faouzi Ghorbel. (2020). "DEPTH MAPS FAST SCALABLE COMPRESSION BASED ON CODING UNIT DEPTH." Web.
1. Sonia Mosbah, Dorsaf Sebai, Faouzi Ghorbel. DEPTH MAPS FAST SCALABLE COMPRESSION BASED ON CODING UNIT DEPTH [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5482

Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary

Paper Details

Authors:
Submitted On:
2 November 2020 - 2:10pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Boundary of Distribution Support Generator (BDSG) Sample Generation on the Boundary.pdf

(24)

Subscribe

[1] , "Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5481. Accessed: Nov. 26, 2020.
@article{5481-20,
url = {http://sigport.org/5481},
author = { },
publisher = {IEEE SigPort},
title = {Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary},
year = {2020} }
TY - EJOUR
T1 - Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5481
ER -
. (2020). Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary. IEEE SigPort. http://sigport.org/5481
, 2020. Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary. Available at: http://sigport.org/5481.
. (2020). "Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary." Web.
1. . Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5481

BROADBAND HYPERSPECTRAL PHASE RETRIEVAL FROM NOISY DATA


Hyperspectral (HS) imaging retrieves information from data obtained across a wide spectral range of spectral channels. The object to reconstruct is a 3D cube, where two coordinates are spatial and the third one is spectral. We assume that this cube is complex-valued, i.e. characterized spatially frequency varying amplitude and phase. The observations are squared magnitudes measured as intensities summarized over the spectrum. The HS phase retrieval problem is formulated as a reconstruction of the HS complex-valued object cube from Gaussian noisy intensity observations.

Paper Details

Authors:
Vladimir Katkovnik; Igor Shevkunov; Karen Egiazarian
Submitted On:
2 November 2020 - 1:26pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation slides, hyperspectral phase retrieval

(13)

Keywords

Additional Categories

Subscribe

[1] Vladimir Katkovnik; Igor Shevkunov; Karen Egiazarian, "BROADBAND HYPERSPECTRAL PHASE RETRIEVAL FROM NOISY DATA", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5480. Accessed: Nov. 26, 2020.
@article{5480-20,
url = {http://sigport.org/5480},
author = {Vladimir Katkovnik; Igor Shevkunov; Karen Egiazarian },
publisher = {IEEE SigPort},
title = {BROADBAND HYPERSPECTRAL PHASE RETRIEVAL FROM NOISY DATA},
year = {2020} }
TY - EJOUR
T1 - BROADBAND HYPERSPECTRAL PHASE RETRIEVAL FROM NOISY DATA
AU - Vladimir Katkovnik; Igor Shevkunov; Karen Egiazarian
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5480
ER -
Vladimir Katkovnik; Igor Shevkunov; Karen Egiazarian. (2020). BROADBAND HYPERSPECTRAL PHASE RETRIEVAL FROM NOISY DATA. IEEE SigPort. http://sigport.org/5480
Vladimir Katkovnik; Igor Shevkunov; Karen Egiazarian, 2020. BROADBAND HYPERSPECTRAL PHASE RETRIEVAL FROM NOISY DATA. Available at: http://sigport.org/5480.
Vladimir Katkovnik; Igor Shevkunov; Karen Egiazarian. (2020). "BROADBAND HYPERSPECTRAL PHASE RETRIEVAL FROM NOISY DATA." Web.
1. Vladimir Katkovnik; Igor Shevkunov; Karen Egiazarian. BROADBAND HYPERSPECTRAL PHASE RETRIEVAL FROM NOISY DATA [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5480

RADAR+RGB Fusion for Robust Object Detection in Autonomous Vehicles


This paper presents two variations of architecture referred to as RANet and BIRANet. The proposed architecture aims to use radar signal data along with RGB camera images to form a robust detection network that works efficiently, even in variable lighting and weather conditions such as rain, dust, fog, and others. First, radar information is fused in the feature extractor network. Second, radar points are used to generate guided anchors. Third, a method is proposed to improve region proposal network targets.

Paper Details

Authors:
Ritu Yadav, Axel Vierling, Karsten Berns
Submitted On:
2 November 2020 - 1:30pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

1953.pdf

(22)

Subscribe

[1] Ritu Yadav, Axel Vierling, Karsten Berns, "RADAR+RGB Fusion for Robust Object Detection in Autonomous Vehicles", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5479. Accessed: Nov. 26, 2020.
@article{5479-20,
url = {http://sigport.org/5479},
author = {Ritu Yadav; Axel Vierling; Karsten Berns },
publisher = {IEEE SigPort},
title = {RADAR+RGB Fusion for Robust Object Detection in Autonomous Vehicles},
year = {2020} }
TY - EJOUR
T1 - RADAR+RGB Fusion for Robust Object Detection in Autonomous Vehicles
AU - Ritu Yadav; Axel Vierling; Karsten Berns
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5479
ER -
Ritu Yadav, Axel Vierling, Karsten Berns. (2020). RADAR+RGB Fusion for Robust Object Detection in Autonomous Vehicles. IEEE SigPort. http://sigport.org/5479
Ritu Yadav, Axel Vierling, Karsten Berns, 2020. RADAR+RGB Fusion for Robust Object Detection in Autonomous Vehicles. Available at: http://sigport.org/5479.
Ritu Yadav, Axel Vierling, Karsten Berns. (2020). "RADAR+RGB Fusion for Robust Object Detection in Autonomous Vehicles." Web.
1. Ritu Yadav, Axel Vierling, Karsten Berns. RADAR+RGB Fusion for Robust Object Detection in Autonomous Vehicles [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5479

Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data


Domain-specific image collections present potential value in various areas of science and business but are often not curated nor have any way to readily extract relevant content. To employ contemporary supervised image analysis methods on such image data, they must first be cleaned and organized, and then manually labeled for the nomenclature employed in the specific domain, which is a time consuming and expensive endeavor.
To address this issue, we designed and implemented the Plud system.

Paper Details

Authors:
Sara Mousavi,Dylan Lee,Tatianna Griffin,kelley cross,Dawnie Steadman, Audris Mockus
Submitted On:
2 November 2020 - 1:10pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

1612presentation.pdf

(8)

Keywords

Additional Categories

Subscribe

[1] Sara Mousavi,Dylan Lee,Tatianna Griffin,kelley cross,Dawnie Steadman, Audris Mockus, "Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5478. Accessed: Nov. 26, 2020.
@article{5478-20,
url = {http://sigport.org/5478},
author = {Sara Mousavi;Dylan Lee;Tatianna Griffin;kelley cross;Dawnie Steadman; Audris Mockus },
publisher = {IEEE SigPort},
title = {Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data},
year = {2020} }
TY - EJOUR
T1 - Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data
AU - Sara Mousavi;Dylan Lee;Tatianna Griffin;kelley cross;Dawnie Steadman; Audris Mockus
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5478
ER -
Sara Mousavi,Dylan Lee,Tatianna Griffin,kelley cross,Dawnie Steadman, Audris Mockus. (2020). Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data. IEEE SigPort. http://sigport.org/5478
Sara Mousavi,Dylan Lee,Tatianna Griffin,kelley cross,Dawnie Steadman, Audris Mockus, 2020. Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data. Available at: http://sigport.org/5478.
Sara Mousavi,Dylan Lee,Tatianna Griffin,kelley cross,Dawnie Steadman, Audris Mockus. (2020). "Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data." Web.
1. Sara Mousavi,Dylan Lee,Tatianna Griffin,kelley cross,Dawnie Steadman, Audris Mockus. Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Data [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5478

Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]

Paper Details

Authors:
Adrián Martín, Gloria Haro, Coloma Ballester
Submitted On:
2 November 2020 - 12:17pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

SlidesICIP.pdf

(10)

Subscribe

[1] Adrián Martín, Gloria Haro, Coloma Ballester, "Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5477. Accessed: Nov. 26, 2020.
@article{5477-20,
url = {http://sigport.org/5477},
author = {Adrián Martín; Gloria Haro; Coloma Ballester },
publisher = {IEEE SigPort},
title = {Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]},
year = {2020} }
TY - EJOUR
T1 - Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]
AU - Adrián Martín; Gloria Haro; Coloma Ballester
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5477
ER -
Adrián Martín, Gloria Haro, Coloma Ballester. (2020). Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]. IEEE SigPort. http://sigport.org/5477
Adrián Martín, Gloria Haro, Coloma Ballester, 2020. Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]. Available at: http://sigport.org/5477.
Adrián Martín, Gloria Haro, Coloma Ballester. (2020). "Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]." Web.
1. Adrián Martín, Gloria Haro, Coloma Ballester. Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides] [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5477

Pages