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

NOVEL VIEW SYNTHESIS WITH SKIP CONNECTIONS


Novel view synthesis is the task of synthesizing an image of an object at an arbitrary viewpoint given one or a few views of the object. The output image of novel view synthesis exhibits a significant structural change from the input. Because of the large change, the skip connections or U-Net architecture, which can sustain the multi-level characteristics of the input images, cannot be directly utilized for the novel view synthesis. In this paper, we investigate several variations of skip connection on two widely used novel view synthesis modules, pixel generation and flow prediction.

Paper Details

Authors:
Juhyeon Kim, Young Min Kim
Submitted On:
3 November 2020 - 3:58am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Novel View Synthesis with Skip Connections (ppt slides) .pdf

(7)

Subscribe

[1] Juhyeon Kim, Young Min Kim, "NOVEL VIEW SYNTHESIS WITH SKIP CONNECTIONS", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5507. Accessed: Nov. 26, 2020.
@article{5507-20,
url = {http://sigport.org/5507},
author = {Juhyeon Kim; Young Min Kim },
publisher = {IEEE SigPort},
title = {NOVEL VIEW SYNTHESIS WITH SKIP CONNECTIONS},
year = {2020} }
TY - EJOUR
T1 - NOVEL VIEW SYNTHESIS WITH SKIP CONNECTIONS
AU - Juhyeon Kim; Young Min Kim
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5507
ER -
Juhyeon Kim, Young Min Kim. (2020). NOVEL VIEW SYNTHESIS WITH SKIP CONNECTIONS. IEEE SigPort. http://sigport.org/5507
Juhyeon Kim, Young Min Kim, 2020. NOVEL VIEW SYNTHESIS WITH SKIP CONNECTIONS. Available at: http://sigport.org/5507.
Juhyeon Kim, Young Min Kim. (2020). "NOVEL VIEW SYNTHESIS WITH SKIP CONNECTIONS." Web.
1. Juhyeon Kim, Young Min Kim. NOVEL VIEW SYNTHESIS WITH SKIP CONNECTIONS [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5507

Real-time semantic background subtraction


Semantic background subtraction (SBS) has been shown to improve the performance of most background subtraction algorithms by combining them with semantic information, derived from a semantic segmentation network. However, SBS requires high-quality semantic segmentation masks for all frames, which are slow to compute. In addition, most state-of-the-art background subtraction algorithms are not real-time, which makes them unsuitable for real-world applications.

Paper Details

Authors:
Anthony Cioppa, Marc Braham, Marc Van Droogenbroeck
Submitted On:
3 November 2020 - 3:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation slides

(10)

Keywords

Additional Categories

Subscribe

[1] Anthony Cioppa, Marc Braham, Marc Van Droogenbroeck, "Real-time semantic background subtraction", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5506. Accessed: Nov. 26, 2020.
@article{5506-20,
url = {http://sigport.org/5506},
author = {Anthony Cioppa; Marc Braham; Marc Van Droogenbroeck },
publisher = {IEEE SigPort},
title = {Real-time semantic background subtraction},
year = {2020} }
TY - EJOUR
T1 - Real-time semantic background subtraction
AU - Anthony Cioppa; Marc Braham; Marc Van Droogenbroeck
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5506
ER -
Anthony Cioppa, Marc Braham, Marc Van Droogenbroeck. (2020). Real-time semantic background subtraction. IEEE SigPort. http://sigport.org/5506
Anthony Cioppa, Marc Braham, Marc Van Droogenbroeck, 2020. Real-time semantic background subtraction. Available at: http://sigport.org/5506.
Anthony Cioppa, Marc Braham, Marc Van Droogenbroeck. (2020). "Real-time semantic background subtraction." Web.
1. Anthony Cioppa, Marc Braham, Marc Van Droogenbroeck. Real-time semantic background subtraction [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5506

Point Set Attention Network for Semantic Segmentation

Paper Details

Authors:
Submitted On:
3 November 2020 - 1:47am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

paper1774.pdf

(12)

Subscribe

[1] , "Point Set Attention Network for Semantic Segmentation", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5505. Accessed: Nov. 26, 2020.
@article{5505-20,
url = {http://sigport.org/5505},
author = { },
publisher = {IEEE SigPort},
title = {Point Set Attention Network for Semantic Segmentation},
year = {2020} }
TY - EJOUR
T1 - Point Set Attention Network for Semantic Segmentation
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5505
ER -
. (2020). Point Set Attention Network for Semantic Segmentation. IEEE SigPort. http://sigport.org/5505
, 2020. Point Set Attention Network for Semantic Segmentation. Available at: http://sigport.org/5505.
. (2020). "Point Set Attention Network for Semantic Segmentation." Web.
1. . Point Set Attention Network for Semantic Segmentation [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5505

3D OBJECT DETECTION USING TEMPORAL LIDAR DATA

Paper Details

Authors:
Scott McCrae, Avideh Zakhor
Submitted On:
3 November 2020 - 1:06am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

McCrae ICIP 2020.pdf

(10)

Subscribe

[1] Scott McCrae, Avideh Zakhor, "3D OBJECT DETECTION USING TEMPORAL LIDAR DATA", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5504. Accessed: Nov. 26, 2020.
@article{5504-20,
url = {http://sigport.org/5504},
author = {Scott McCrae; Avideh Zakhor },
publisher = {IEEE SigPort},
title = {3D OBJECT DETECTION USING TEMPORAL LIDAR DATA},
year = {2020} }
TY - EJOUR
T1 - 3D OBJECT DETECTION USING TEMPORAL LIDAR DATA
AU - Scott McCrae; Avideh Zakhor
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5504
ER -
Scott McCrae, Avideh Zakhor. (2020). 3D OBJECT DETECTION USING TEMPORAL LIDAR DATA. IEEE SigPort. http://sigport.org/5504
Scott McCrae, Avideh Zakhor, 2020. 3D OBJECT DETECTION USING TEMPORAL LIDAR DATA. Available at: http://sigport.org/5504.
Scott McCrae, Avideh Zakhor. (2020). "3D OBJECT DETECTION USING TEMPORAL LIDAR DATA." Web.
1. Scott McCrae, Avideh Zakhor. 3D OBJECT DETECTION USING TEMPORAL LIDAR DATA [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5504

An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images

Paper Details

Authors:
Lifeng Yan, Xiaoqing Liu, Yizhou Yu, Sanyuan Zhang
Submitted On:
3 November 2020 - 12:36am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images.pdf

(7)

Subscribe

[1] Lifeng Yan, Xiaoqing Liu, Yizhou Yu, Sanyuan Zhang, "An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5503. Accessed: Nov. 26, 2020.
@article{5503-20,
url = {http://sigport.org/5503},
author = {Lifeng Yan; Xiaoqing Liu; Yizhou Yu; Sanyuan Zhang },
publisher = {IEEE SigPort},
title = {An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images},
year = {2020} }
TY - EJOUR
T1 - An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images
AU - Lifeng Yan; Xiaoqing Liu; Yizhou Yu; Sanyuan Zhang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5503
ER -
Lifeng Yan, Xiaoqing Liu, Yizhou Yu, Sanyuan Zhang. (2020). An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images. IEEE SigPort. http://sigport.org/5503
Lifeng Yan, Xiaoqing Liu, Yizhou Yu, Sanyuan Zhang, 2020. An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images. Available at: http://sigport.org/5503.
Lifeng Yan, Xiaoqing Liu, Yizhou Yu, Sanyuan Zhang. (2020). "An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images." Web.
1. Lifeng Yan, Xiaoqing Liu, Yizhou Yu, Sanyuan Zhang. An End-To-End Network For Detecting Multi-Domain Fractures On X-Ray Images [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5503

CSIOR:An Algorithm for Ordered Triangular Mesh Regularization


3D scanners generate irregularly distributed cloud of points in
most of the cases. Dealing with such data, often in the form of
triangular meshes, requires a pre-processing step to regularize
the triangle facets shape and size. In this paper, we propose
CSIOR, a novel mesh regularization technique which is capable
of producing quasi-equilateral triangles, and distinguished
by two novel features, namely, its intrinsic ordered aspect and
its preservation of the geometric texture of the surface (relief

Paper Details

Authors:
Submitted On:
3 November 2020 - 12:23am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Presentation.pdf

(48)

Subscribe

[1] , "CSIOR:An Algorithm for Ordered Triangular Mesh Regularization", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5502. Accessed: Nov. 26, 2020.
@article{5502-20,
url = {http://sigport.org/5502},
author = { },
publisher = {IEEE SigPort},
title = {CSIOR:An Algorithm for Ordered Triangular Mesh Regularization},
year = {2020} }
TY - EJOUR
T1 - CSIOR:An Algorithm for Ordered Triangular Mesh Regularization
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5502
ER -
. (2020). CSIOR:An Algorithm for Ordered Triangular Mesh Regularization. IEEE SigPort. http://sigport.org/5502
, 2020. CSIOR:An Algorithm for Ordered Triangular Mesh Regularization. Available at: http://sigport.org/5502.
. (2020). "CSIOR:An Algorithm for Ordered Triangular Mesh Regularization." Web.
1. . CSIOR:An Algorithm for Ordered Triangular Mesh Regularization [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5502

A BAND ATTENTION AWARE ENSEMBLE NETWORK FOR HYPERSPECTRAL OBJECT TRACKING


Hyperspectral videos contain images with a large number of light wavelength indexed bands that can facilitate material
identification for object tracking. Most hyperspectral trackers use hand-crafted features rather than deep learning gener-
ated features for image representation due to limited training samples. To fill this gap, this paper introduces a band atten-
tion aware ensemble network (BAE-Net) for deep hyperspectral object tracking, which takes advantages of deep models

Paper Details

Authors:
Zhuanfeng Li; Fengchao Xiong; Jun Zhou; Jing Wang; Jianfeng Lu;Yuntao Qian
Submitted On:
3 November 2020 - 12:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster pdf and slides , presentation slides

(5)

Subscribe

[1] Zhuanfeng Li; Fengchao Xiong; Jun Zhou; Jing Wang; Jianfeng Lu;Yuntao Qian, "A BAND ATTENTION AWARE ENSEMBLE NETWORK FOR HYPERSPECTRAL OBJECT TRACKING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5501. Accessed: Nov. 26, 2020.
@article{5501-20,
url = {http://sigport.org/5501},
author = {Zhuanfeng Li; Fengchao Xiong; Jun Zhou; Jing Wang; Jianfeng Lu;Yuntao Qian },
publisher = {IEEE SigPort},
title = {A BAND ATTENTION AWARE ENSEMBLE NETWORK FOR HYPERSPECTRAL OBJECT TRACKING},
year = {2020} }
TY - EJOUR
T1 - A BAND ATTENTION AWARE ENSEMBLE NETWORK FOR HYPERSPECTRAL OBJECT TRACKING
AU - Zhuanfeng Li; Fengchao Xiong; Jun Zhou; Jing Wang; Jianfeng Lu;Yuntao Qian
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5501
ER -
Zhuanfeng Li; Fengchao Xiong; Jun Zhou; Jing Wang; Jianfeng Lu;Yuntao Qian. (2020). A BAND ATTENTION AWARE ENSEMBLE NETWORK FOR HYPERSPECTRAL OBJECT TRACKING. IEEE SigPort. http://sigport.org/5501
Zhuanfeng Li; Fengchao Xiong; Jun Zhou; Jing Wang; Jianfeng Lu;Yuntao Qian, 2020. A BAND ATTENTION AWARE ENSEMBLE NETWORK FOR HYPERSPECTRAL OBJECT TRACKING. Available at: http://sigport.org/5501.
Zhuanfeng Li; Fengchao Xiong; Jun Zhou; Jing Wang; Jianfeng Lu;Yuntao Qian. (2020). "A BAND ATTENTION AWARE ENSEMBLE NETWORK FOR HYPERSPECTRAL OBJECT TRACKING." Web.
1. Zhuanfeng Li; Fengchao Xiong; Jun Zhou; Jing Wang; Jianfeng Lu;Yuntao Qian. A BAND ATTENTION AWARE ENSEMBLE NETWORK FOR HYPERSPECTRAL OBJECT TRACKING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5501

EMPIRICAL ANALYSIS OF OVERFITTING AND MODE DROP IN GAN TRAINING


We examine two key questions in GAN training, namely overfitting and mode drop, from an empirical perspective. We show that when stochasticity is removed from the training procedure, GANs can overfit and exhibit almost no mode drop. Our results shed light on important characteristics of the GAN training procedure. They also provide evidence against prevailing intuitions that GANs do not memorize the training set, and that mode dropping is mainly due to properties of the GAN objective rather than how it is optimized during training.

Paper Details

Authors:
Chuan-Sheng Foo, Kim-Hui Yap, Vijay Chandrasekhar
Submitted On:
3 November 2020 - 12:06am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2020_Presentation.pptx

(4)

Subscribe

[1] Chuan-Sheng Foo, Kim-Hui Yap, Vijay Chandrasekhar, "EMPIRICAL ANALYSIS OF OVERFITTING AND MODE DROP IN GAN TRAINING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5500. Accessed: Nov. 26, 2020.
@article{5500-20,
url = {http://sigport.org/5500},
author = {Chuan-Sheng Foo; Kim-Hui Yap; Vijay Chandrasekhar },
publisher = {IEEE SigPort},
title = {EMPIRICAL ANALYSIS OF OVERFITTING AND MODE DROP IN GAN TRAINING},
year = {2020} }
TY - EJOUR
T1 - EMPIRICAL ANALYSIS OF OVERFITTING AND MODE DROP IN GAN TRAINING
AU - Chuan-Sheng Foo; Kim-Hui Yap; Vijay Chandrasekhar
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5500
ER -
Chuan-Sheng Foo, Kim-Hui Yap, Vijay Chandrasekhar. (2020). EMPIRICAL ANALYSIS OF OVERFITTING AND MODE DROP IN GAN TRAINING. IEEE SigPort. http://sigport.org/5500
Chuan-Sheng Foo, Kim-Hui Yap, Vijay Chandrasekhar, 2020. EMPIRICAL ANALYSIS OF OVERFITTING AND MODE DROP IN GAN TRAINING. Available at: http://sigport.org/5500.
Chuan-Sheng Foo, Kim-Hui Yap, Vijay Chandrasekhar. (2020). "EMPIRICAL ANALYSIS OF OVERFITTING AND MODE DROP IN GAN TRAINING." Web.
1. Chuan-Sheng Foo, Kim-Hui Yap, Vijay Chandrasekhar. EMPIRICAL ANALYSIS OF OVERFITTING AND MODE DROP IN GAN TRAINING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5500

EMOTION TRANSFORMATION FEATURE: NOVEL FEATURE FOR DECEPTION DETECTION IN VIDEOS


Deception detection has been a hot research topic in many areas such as jurisprudence, law enforcement, business, and computer vision. However, there are still many problems that are worth more investigation. One of the major challenges is the data scarcity problem. So far, only one multi-modal benchmark dataset on deception detection has been published, which contains 121 video clips for deception detection (61 for deceptive class and 60 for truthful class).

Paper Details

Authors:
Jun-Teng Yang, Guei-Ming Liu, Scott C.-H Huang
Submitted On:
2 November 2020 - 11:20pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP2020_PresentationSlides.pdf

(8)

Subscribe

[1] Jun-Teng Yang, Guei-Ming Liu, Scott C.-H Huang, "EMOTION TRANSFORMATION FEATURE: NOVEL FEATURE FOR DECEPTION DETECTION IN VIDEOS", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5499. Accessed: Nov. 26, 2020.
@article{5499-20,
url = {http://sigport.org/5499},
author = {Jun-Teng Yang; Guei-Ming Liu; Scott C.-H Huang },
publisher = {IEEE SigPort},
title = {EMOTION TRANSFORMATION FEATURE: NOVEL FEATURE FOR DECEPTION DETECTION IN VIDEOS},
year = {2020} }
TY - EJOUR
T1 - EMOTION TRANSFORMATION FEATURE: NOVEL FEATURE FOR DECEPTION DETECTION IN VIDEOS
AU - Jun-Teng Yang; Guei-Ming Liu; Scott C.-H Huang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5499
ER -
Jun-Teng Yang, Guei-Ming Liu, Scott C.-H Huang. (2020). EMOTION TRANSFORMATION FEATURE: NOVEL FEATURE FOR DECEPTION DETECTION IN VIDEOS. IEEE SigPort. http://sigport.org/5499
Jun-Teng Yang, Guei-Ming Liu, Scott C.-H Huang, 2020. EMOTION TRANSFORMATION FEATURE: NOVEL FEATURE FOR DECEPTION DETECTION IN VIDEOS. Available at: http://sigport.org/5499.
Jun-Teng Yang, Guei-Ming Liu, Scott C.-H Huang. (2020). "EMOTION TRANSFORMATION FEATURE: NOVEL FEATURE FOR DECEPTION DETECTION IN VIDEOS." Web.
1. Jun-Teng Yang, Guei-Ming Liu, Scott C.-H Huang. EMOTION TRANSFORMATION FEATURE: NOVEL FEATURE FOR DECEPTION DETECTION IN VIDEOS [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5499

Identity-invariant Facial Landmark Frontalization for Facial Expression Analysis


We propose a frontalization technique for 2D facial land- marks, designed to aid in the analysis of facial expressions. It employs a new normalization strategy aiming to minimize identity variations, by displacing groups of facial landmarks to standardized locations. The technique operates directly on 2D landmark coordinates, does not require additional feature extraction and as such is computationally light. It achieves considerable improvement over a reference approach, justifying its use as an efficient preprocessing step for facial expression analysis based on geometric features.

Paper Details

Authors:
Vassilios Vonikakis, Stefan Winkler
Submitted On:
2 November 2020 - 9:44pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation_final.pdf

(9)

Keywords

Additional Categories

Subscribe

[1] Vassilios Vonikakis, Stefan Winkler, "Identity-invariant Facial Landmark Frontalization for Facial Expression Analysis", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5498. Accessed: Nov. 26, 2020.
@article{5498-20,
url = {http://sigport.org/5498},
author = {Vassilios Vonikakis; Stefan Winkler },
publisher = {IEEE SigPort},
title = {Identity-invariant Facial Landmark Frontalization for Facial Expression Analysis},
year = {2020} }
TY - EJOUR
T1 - Identity-invariant Facial Landmark Frontalization for Facial Expression Analysis
AU - Vassilios Vonikakis; Stefan Winkler
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5498
ER -
Vassilios Vonikakis, Stefan Winkler. (2020). Identity-invariant Facial Landmark Frontalization for Facial Expression Analysis. IEEE SigPort. http://sigport.org/5498
Vassilios Vonikakis, Stefan Winkler, 2020. Identity-invariant Facial Landmark Frontalization for Facial Expression Analysis. Available at: http://sigport.org/5498.
Vassilios Vonikakis, Stefan Winkler. (2020). "Identity-invariant Facial Landmark Frontalization for Facial Expression Analysis." Web.
1. Vassilios Vonikakis, Stefan Winkler. Identity-invariant Facial Landmark Frontalization for Facial Expression Analysis [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5498

Pages