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

ICIP 2019

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.

Enhanced Video Compression based on Effective Bit depth Adaptation

Paper Details

Authors:
Submitted On:
23 September 2019 - 8:53pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

SLIDES_ICIP_2019_EBDA.pdf

(31)

Subscribe

[1] , "Enhanced Video Compression based on Effective Bit depth Adaptation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4824. Accessed: Jan. 26, 2020.
@article{4824-19,
url = {http://sigport.org/4824},
author = { },
publisher = {IEEE SigPort},
title = {Enhanced Video Compression based on Effective Bit depth Adaptation},
year = {2019} }
TY - EJOUR
T1 - Enhanced Video Compression based on Effective Bit depth Adaptation
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4824
ER -
. (2019). Enhanced Video Compression based on Effective Bit depth Adaptation. IEEE SigPort. http://sigport.org/4824
, 2019. Enhanced Video Compression based on Effective Bit depth Adaptation. Available at: http://sigport.org/4824.
. (2019). "Enhanced Video Compression based on Effective Bit depth Adaptation." Web.
1. . Enhanced Video Compression based on Effective Bit depth Adaptation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4824

IDENTIFICATION OF BUILDINGS IN STREET IMAGES USING MAP INFORMATION

Paper Details

Authors:
Masanori Ogawa,Kiyoharu Aizawa
Submitted On:
23 September 2019 - 6:12pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019.pdf

(31)

Subscribe

[1] Masanori Ogawa,Kiyoharu Aizawa, "IDENTIFICATION OF BUILDINGS IN STREET IMAGES USING MAP INFORMATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4823. Accessed: Jan. 26, 2020.
@article{4823-19,
url = {http://sigport.org/4823},
author = {Masanori Ogawa;Kiyoharu Aizawa },
publisher = {IEEE SigPort},
title = {IDENTIFICATION OF BUILDINGS IN STREET IMAGES USING MAP INFORMATION},
year = {2019} }
TY - EJOUR
T1 - IDENTIFICATION OF BUILDINGS IN STREET IMAGES USING MAP INFORMATION
AU - Masanori Ogawa;Kiyoharu Aizawa
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4823
ER -
Masanori Ogawa,Kiyoharu Aizawa. (2019). IDENTIFICATION OF BUILDINGS IN STREET IMAGES USING MAP INFORMATION. IEEE SigPort. http://sigport.org/4823
Masanori Ogawa,Kiyoharu Aizawa, 2019. IDENTIFICATION OF BUILDINGS IN STREET IMAGES USING MAP INFORMATION. Available at: http://sigport.org/4823.
Masanori Ogawa,Kiyoharu Aizawa. (2019). "IDENTIFICATION OF BUILDINGS IN STREET IMAGES USING MAP INFORMATION." Web.
1. Masanori Ogawa,Kiyoharu Aizawa. IDENTIFICATION OF BUILDINGS IN STREET IMAGES USING MAP INFORMATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4823

Exact Incremental and Decremental Learning for LS-SVM


In this paper, we present a novel incremental and decremental learning method for the least-squares support vector machine (LS-SVM). The goal is to adapt a pre-trained model to changes in the training dataset, without retraining the model on all the data, where the changes can include addition and deletion of data samples. We propose a provably exact method where the updated model is exactly the same as a model trained from scratch using the entire (updated) training dataset.

Paper Details

Authors:
Wei-Han Lee, Bong Jun Ko, Shiqiang Wang, Changchang Liu, Kin K. Leung
Submitted On:
23 September 2019 - 12:50pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP 2019 talk.pdf

(28)

Subscribe

[1] Wei-Han Lee, Bong Jun Ko, Shiqiang Wang, Changchang Liu, Kin K. Leung, "Exact Incremental and Decremental Learning for LS-SVM", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4822. Accessed: Jan. 26, 2020.
@article{4822-19,
url = {http://sigport.org/4822},
author = {Wei-Han Lee; Bong Jun Ko; Shiqiang Wang; Changchang Liu; Kin K. Leung },
publisher = {IEEE SigPort},
title = {Exact Incremental and Decremental Learning for LS-SVM},
year = {2019} }
TY - EJOUR
T1 - Exact Incremental and Decremental Learning for LS-SVM
AU - Wei-Han Lee; Bong Jun Ko; Shiqiang Wang; Changchang Liu; Kin K. Leung
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4822
ER -
Wei-Han Lee, Bong Jun Ko, Shiqiang Wang, Changchang Liu, Kin K. Leung. (2019). Exact Incremental and Decremental Learning for LS-SVM. IEEE SigPort. http://sigport.org/4822
Wei-Han Lee, Bong Jun Ko, Shiqiang Wang, Changchang Liu, Kin K. Leung, 2019. Exact Incremental and Decremental Learning for LS-SVM. Available at: http://sigport.org/4822.
Wei-Han Lee, Bong Jun Ko, Shiqiang Wang, Changchang Liu, Kin K. Leung. (2019). "Exact Incremental and Decremental Learning for LS-SVM." Web.
1. Wei-Han Lee, Bong Jun Ko, Shiqiang Wang, Changchang Liu, Kin K. Leung. Exact Incremental and Decremental Learning for LS-SVM [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4822

DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU


High-throughput JPEG2000 (HTJ2K), also known as JPEG 2000 Part 15, is the most recent addition to the JPEG2000 suite of coding tools. The file extension JPH has been designated for compressed images employing this new part of the standard. This new part describes a “fast” block coder for the JPEG 2000 format, while retaining most other JPEG2000 features and capabilities intact.

Paper Details

Authors:
Submitted On:
24 September 2019 - 10:49am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU

(49)

Subscribe

[1] , "DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4820. Accessed: Jan. 26, 2020.
@article{4820-19,
url = {http://sigport.org/4820},
author = { },
publisher = {IEEE SigPort},
title = {DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU},
year = {2019} }
TY - EJOUR
T1 - DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4820
ER -
. (2019). DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU. IEEE SigPort. http://sigport.org/4820
, 2019. DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU. Available at: http://sigport.org/4820.
. (2019). "DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU." Web.
1. . DECODING HIGH-THROUGHPUT JPEG2000 (HTJ2K) ON A GPU [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4820

JOINT LEARNING OF SELF-REPRESENTATION AND INDICATOR FOR MULTI-VIEW IMAGE CLUSTERING

Paper Details

Authors:
Zhiqiang Lu, Hao Tang, Yan Yan, Songhao Zhu, Xiao-Yuan Jing, Zuoyong Li
Submitted On:
23 September 2019 - 4:37pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip 2019 poster: multi-view image clustering

(33)

Subscribe

[1] Zhiqiang Lu, Hao Tang, Yan Yan, Songhao Zhu, Xiao-Yuan Jing, Zuoyong Li, "JOINT LEARNING OF SELF-REPRESENTATION AND INDICATOR FOR MULTI-VIEW IMAGE CLUSTERING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4819. Accessed: Jan. 26, 2020.
@article{4819-19,
url = {http://sigport.org/4819},
author = {Zhiqiang Lu; Hao Tang; Yan Yan; Songhao Zhu; Xiao-Yuan Jing; Zuoyong Li },
publisher = {IEEE SigPort},
title = {JOINT LEARNING OF SELF-REPRESENTATION AND INDICATOR FOR MULTI-VIEW IMAGE CLUSTERING},
year = {2019} }
TY - EJOUR
T1 - JOINT LEARNING OF SELF-REPRESENTATION AND INDICATOR FOR MULTI-VIEW IMAGE CLUSTERING
AU - Zhiqiang Lu; Hao Tang; Yan Yan; Songhao Zhu; Xiao-Yuan Jing; Zuoyong Li
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4819
ER -
Zhiqiang Lu, Hao Tang, Yan Yan, Songhao Zhu, Xiao-Yuan Jing, Zuoyong Li. (2019). JOINT LEARNING OF SELF-REPRESENTATION AND INDICATOR FOR MULTI-VIEW IMAGE CLUSTERING. IEEE SigPort. http://sigport.org/4819
Zhiqiang Lu, Hao Tang, Yan Yan, Songhao Zhu, Xiao-Yuan Jing, Zuoyong Li, 2019. JOINT LEARNING OF SELF-REPRESENTATION AND INDICATOR FOR MULTI-VIEW IMAGE CLUSTERING. Available at: http://sigport.org/4819.
Zhiqiang Lu, Hao Tang, Yan Yan, Songhao Zhu, Xiao-Yuan Jing, Zuoyong Li. (2019). "JOINT LEARNING OF SELF-REPRESENTATION AND INDICATOR FOR MULTI-VIEW IMAGE CLUSTERING." Web.
1. Zhiqiang Lu, Hao Tang, Yan Yan, Songhao Zhu, Xiao-Yuan Jing, Zuoyong Li. JOINT LEARNING OF SELF-REPRESENTATION AND INDICATOR FOR MULTI-VIEW IMAGE CLUSTERING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4819

RELAXED ORIENTED IMAGE FORESTING TRANSFORM FOR SEEDED IMAGE SEGMENTATION


In this work, we propose a hybrid method for seeded image segmentation, named Relaxed OIFT, which extends a method by Malmberg et al. to directed graphs, to properly incorporate the boundary polarity constraint. Relaxed OIFT lies between the pure Oriented Image Foresting Transform (OIFT) at one end and the extension of Random Walks (RW) to directed graphs as proposed by Singaraju et al. Relaxed OIFT is evaluated in MR and CT medical images, producing more intuitively correct segmentation results than both OIFT and RW, and being easy to be extended to multi-dimensional images.

Paper Details

Authors:
Caio L. Demario, Paulo A.V. Miranda
Submitted On:
22 September 2019 - 6:12pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

RelaxedOIFT_ICIP19

(21)

Subscribe

[1] Caio L. Demario, Paulo A.V. Miranda, "RELAXED ORIENTED IMAGE FORESTING TRANSFORM FOR SEEDED IMAGE SEGMENTATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4818. Accessed: Jan. 26, 2020.
@article{4818-19,
url = {http://sigport.org/4818},
author = {Caio L. Demario; Paulo A.V. Miranda },
publisher = {IEEE SigPort},
title = {RELAXED ORIENTED IMAGE FORESTING TRANSFORM FOR SEEDED IMAGE SEGMENTATION},
year = {2019} }
TY - EJOUR
T1 - RELAXED ORIENTED IMAGE FORESTING TRANSFORM FOR SEEDED IMAGE SEGMENTATION
AU - Caio L. Demario; Paulo A.V. Miranda
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4818
ER -
Caio L. Demario, Paulo A.V. Miranda. (2019). RELAXED ORIENTED IMAGE FORESTING TRANSFORM FOR SEEDED IMAGE SEGMENTATION. IEEE SigPort. http://sigport.org/4818
Caio L. Demario, Paulo A.V. Miranda, 2019. RELAXED ORIENTED IMAGE FORESTING TRANSFORM FOR SEEDED IMAGE SEGMENTATION. Available at: http://sigport.org/4818.
Caio L. Demario, Paulo A.V. Miranda. (2019). "RELAXED ORIENTED IMAGE FORESTING TRANSFORM FOR SEEDED IMAGE SEGMENTATION." Web.
1. Caio L. Demario, Paulo A.V. Miranda. RELAXED ORIENTED IMAGE FORESTING TRANSFORM FOR SEEDED IMAGE SEGMENTATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4818

Single-image rain removal via multi-scale cascading image generation


A novel single-image rain removal method is proposed based on multi-scale cascading image generation (MSCG). In particular, the proposed method consists of an encoder extracting multi-scale features from images and a decoder generating de-rained images with a cascading mechanism. The encoder ensembles the convolution neural networks using the kernels with different sizes, and integrates their outputs across different scales.

Paper Details

Authors:
Zheng Zhang, Yi Xu, He Wang, Bingbing Ni, Hongteng Xu
Submitted On:
22 September 2019 - 2:38pm
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

Poster ICIP 2019 Paper #2542.pdf

(29)

Subscribe

[1] Zheng Zhang, Yi Xu, He Wang, Bingbing Ni, Hongteng Xu, "Single-image rain removal via multi-scale cascading image generation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4817. Accessed: Jan. 26, 2020.
@article{4817-19,
url = {http://sigport.org/4817},
author = {Zheng Zhang; Yi Xu; He Wang; Bingbing Ni; Hongteng Xu },
publisher = {IEEE SigPort},
title = {Single-image rain removal via multi-scale cascading image generation},
year = {2019} }
TY - EJOUR
T1 - Single-image rain removal via multi-scale cascading image generation
AU - Zheng Zhang; Yi Xu; He Wang; Bingbing Ni; Hongteng Xu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4817
ER -
Zheng Zhang, Yi Xu, He Wang, Bingbing Ni, Hongteng Xu. (2019). Single-image rain removal via multi-scale cascading image generation. IEEE SigPort. http://sigport.org/4817
Zheng Zhang, Yi Xu, He Wang, Bingbing Ni, Hongteng Xu, 2019. Single-image rain removal via multi-scale cascading image generation. Available at: http://sigport.org/4817.
Zheng Zhang, Yi Xu, He Wang, Bingbing Ni, Hongteng Xu. (2019). "Single-image rain removal via multi-scale cascading image generation." Web.
1. Zheng Zhang, Yi Xu, He Wang, Bingbing Ni, Hongteng Xu. Single-image rain removal via multi-scale cascading image generation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4817

A No-Reference Autoencoder Video Quality Metric


In this work, we introduce the No-reference Autoencoder VidEo (NAVE) quality metric, which is based on a deep au-toencoder machine learning technique. The metric uses a set of spatial and temporal features to estimate the overall visual quality, taking advantage of the autoencoder ability to produce a better and more compact set of features. NAVE was tested on two databases: the UnB-AVQ database and the LiveNetflix-II database.

Paper Details

Authors:
Helard B. Martinez ; Mylène C. Q. Farias ; Andrew Hines
Submitted On:
22 September 2019 - 12:53pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2019-09-ICIP-presentation.pdf

(41)

Subscribe

[1] Helard B. Martinez ; Mylène C. Q. Farias ; Andrew Hines , "A No-Reference Autoencoder Video Quality Metric", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4816. Accessed: Jan. 26, 2020.
@article{4816-19,
url = {http://sigport.org/4816},
author = { Helard B. Martinez ; Mylène C. Q. Farias ; Andrew Hines },
publisher = {IEEE SigPort},
title = {A No-Reference Autoencoder Video Quality Metric},
year = {2019} }
TY - EJOUR
T1 - A No-Reference Autoencoder Video Quality Metric
AU - Helard B. Martinez ; Mylène C. Q. Farias ; Andrew Hines
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4816
ER -
Helard B. Martinez ; Mylène C. Q. Farias ; Andrew Hines . (2019). A No-Reference Autoencoder Video Quality Metric. IEEE SigPort. http://sigport.org/4816
Helard B. Martinez ; Mylène C. Q. Farias ; Andrew Hines , 2019. A No-Reference Autoencoder Video Quality Metric. Available at: http://sigport.org/4816.
Helard B. Martinez ; Mylène C. Q. Farias ; Andrew Hines . (2019). "A No-Reference Autoencoder Video Quality Metric." Web.
1. Helard B. Martinez ; Mylène C. Q. Farias ; Andrew Hines . A No-Reference Autoencoder Video Quality Metric [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4816

Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints


We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and combine it with a least squares solution for the inverse 2D to 3D geometric mapping problem, using the camera projection matrix. The closed-form solution of the mathematical system, along with the initial output of the adapted Faster R-CNN are then passed through a final ShiftNet network that refines the result using our newly proposed Volume Displacement Loss.

Paper Details

Authors:
Andretti Naiden,Vlad Paunescu,Gyeongmo Kim,ByeongMoon Jeon,Marius Leordeanu
Submitted On:
22 September 2019 - 3:45am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

shift-rcnn-icip2019_prefinal.pdf

(47)

Subscribe

[1] Andretti Naiden,Vlad Paunescu,Gyeongmo Kim,ByeongMoon Jeon,Marius Leordeanu, "Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4815. Accessed: Jan. 26, 2020.
@article{4815-19,
url = {http://sigport.org/4815},
author = {Andretti Naiden;Vlad Paunescu;Gyeongmo Kim;ByeongMoon Jeon;Marius Leordeanu },
publisher = {IEEE SigPort},
title = {Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints},
year = {2019} }
TY - EJOUR
T1 - Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints
AU - Andretti Naiden;Vlad Paunescu;Gyeongmo Kim;ByeongMoon Jeon;Marius Leordeanu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4815
ER -
Andretti Naiden,Vlad Paunescu,Gyeongmo Kim,ByeongMoon Jeon,Marius Leordeanu. (2019). Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints. IEEE SigPort. http://sigport.org/4815
Andretti Naiden,Vlad Paunescu,Gyeongmo Kim,ByeongMoon Jeon,Marius Leordeanu, 2019. Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints. Available at: http://sigport.org/4815.
Andretti Naiden,Vlad Paunescu,Gyeongmo Kim,ByeongMoon Jeon,Marius Leordeanu. (2019). "Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints." Web.
1. Andretti Naiden,Vlad Paunescu,Gyeongmo Kim,ByeongMoon Jeon,Marius Leordeanu. Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4815

3D Shape Retrieval Through Multilayer RBF Neural Network


3D object retrieval involves more efforts mainly because major computer vision features are designed for 2D images, which is rarely applicable for 3D models. In this paper, we propose to retrieve the 3D models based on the implicit parameters learned from the radial base functions that represent the 3D objects. The radial base functions are learned from the RBF neural network. As deep neural networks can represent the data that is not linearly separable, we apply multiple layers' neural network to train the radial base functions.

Paper Details

Authors:
Yahong Han
Submitted On:
22 September 2019 - 12:37am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

icip3549.pdf

(34)

Subscribe

[1] Yahong Han, "3D Shape Retrieval Through Multilayer RBF Neural Network", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4813. Accessed: Jan. 26, 2020.
@article{4813-19,
url = {http://sigport.org/4813},
author = {Yahong Han },
publisher = {IEEE SigPort},
title = {3D Shape Retrieval Through Multilayer RBF Neural Network},
year = {2019} }
TY - EJOUR
T1 - 3D Shape Retrieval Through Multilayer RBF Neural Network
AU - Yahong Han
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4813
ER -
Yahong Han. (2019). 3D Shape Retrieval Through Multilayer RBF Neural Network. IEEE SigPort. http://sigport.org/4813
Yahong Han, 2019. 3D Shape Retrieval Through Multilayer RBF Neural Network. Available at: http://sigport.org/4813.
Yahong Han. (2019). "3D Shape Retrieval Through Multilayer RBF Neural Network." Web.
1. Yahong Han. 3D Shape Retrieval Through Multilayer RBF Neural Network [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4813

Pages