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

Image, Video, and Multidimensional Signal Processing

Progressive Filtering for Feature Matching


In this paper, we propose a simple yet efficient method termed as Progressive Filtering for Feature Matching, which is able to establish accurate correspondences between two images of common or similar scenes. Our algorithm first grids the correspondence space and calculates a typical motion vector for each cell, and then removes false matches by checking the consistency between each putative match and the typical motion vector in the corresponding cell, which is achieved by a convolution operation.

Paper Details

Authors:
Xingyu Jiang, Jiayi Ma, Jun Chen
Submitted On:
8 May 2019 - 9:46am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

poster11.pdf

(51)

Subscribe

[1] Xingyu Jiang, Jiayi Ma, Jun Chen, "Progressive Filtering for Feature Matching", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4100. Accessed: Oct. 22, 2019.
@article{4100-19,
url = {http://sigport.org/4100},
author = {Xingyu Jiang; Jiayi Ma; Jun Chen },
publisher = {IEEE SigPort},
title = {Progressive Filtering for Feature Matching},
year = {2019} }
TY - EJOUR
T1 - Progressive Filtering for Feature Matching
AU - Xingyu Jiang; Jiayi Ma; Jun Chen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4100
ER -
Xingyu Jiang, Jiayi Ma, Jun Chen. (2019). Progressive Filtering for Feature Matching. IEEE SigPort. http://sigport.org/4100
Xingyu Jiang, Jiayi Ma, Jun Chen, 2019. Progressive Filtering for Feature Matching. Available at: http://sigport.org/4100.
Xingyu Jiang, Jiayi Ma, Jun Chen. (2019). "Progressive Filtering for Feature Matching." Web.
1. Xingyu Jiang, Jiayi Ma, Jun Chen. Progressive Filtering for Feature Matching [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4100

CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS


In this paper, we optimize the computations of third-order low-tubal-rank tensor operations on many-core GPUs. Tensor operations are compute-intensive and existing studies optimize such operations in a case-by-case manner, which can be inefficient and error-prone. We develop and optimize a BLAS-like library for the low-tubal-rank tensor model called cuTensor-tubal, which includes efficient GPU primitives for tensor operations and key processes. We compute tensor operations in the frequency domain and fully exploit tube-wise and slice-wise parallelisms.

Paper Details

Authors:
Tao Zhang, Xiao-Yang Liu
Submitted On:
8 May 2019 - 8:21am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

The poster for paper entitled "CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS"

(60)

Subscribe

[1] Tao Zhang, Xiao-Yang Liu, "CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4082. Accessed: Oct. 22, 2019.
@article{4082-19,
url = {http://sigport.org/4082},
author = {Tao Zhang; Xiao-Yang Liu },
publisher = {IEEE SigPort},
title = {CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS},
year = {2019} }
TY - EJOUR
T1 - CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS
AU - Tao Zhang; Xiao-Yang Liu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4082
ER -
Tao Zhang, Xiao-Yang Liu. (2019). CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS. IEEE SigPort. http://sigport.org/4082
Tao Zhang, Xiao-Yang Liu, 2019. CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS. Available at: http://sigport.org/4082.
Tao Zhang, Xiao-Yang Liu. (2019). "CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS." Web.
1. Tao Zhang, Xiao-Yang Liu. CUTENSOR-TUBAL: OPTIMIZED GPU LIBRARY FOR LOW-TUBAL-RANK TENSORS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4082

Classification of Severely Occluded Image Sequences via Convolutional Recurrent Neural Networks

Paper Details

Authors:
Jian Zheng, Yifan Wang, Xiaonan Zhang, Xiaohua Li
Submitted On:
29 November 2018 - 3:44am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

GlobalSIP_poster_Final.pdf

(111)

Subscribe

[1] Jian Zheng, Yifan Wang, Xiaonan Zhang, Xiaohua Li, "Classification of Severely Occluded Image Sequences via Convolutional Recurrent Neural Networks", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3830. Accessed: Oct. 22, 2019.
@article{3830-18,
url = {http://sigport.org/3830},
author = {Jian Zheng; Yifan Wang; Xiaonan Zhang; Xiaohua Li },
publisher = {IEEE SigPort},
title = {Classification of Severely Occluded Image Sequences via Convolutional Recurrent Neural Networks},
year = {2018} }
TY - EJOUR
T1 - Classification of Severely Occluded Image Sequences via Convolutional Recurrent Neural Networks
AU - Jian Zheng; Yifan Wang; Xiaonan Zhang; Xiaohua Li
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3830
ER -
Jian Zheng, Yifan Wang, Xiaonan Zhang, Xiaohua Li. (2018). Classification of Severely Occluded Image Sequences via Convolutional Recurrent Neural Networks. IEEE SigPort. http://sigport.org/3830
Jian Zheng, Yifan Wang, Xiaonan Zhang, Xiaohua Li, 2018. Classification of Severely Occluded Image Sequences via Convolutional Recurrent Neural Networks. Available at: http://sigport.org/3830.
Jian Zheng, Yifan Wang, Xiaonan Zhang, Xiaohua Li. (2018). "Classification of Severely Occluded Image Sequences via Convolutional Recurrent Neural Networks." Web.
1. Jian Zheng, Yifan Wang, Xiaonan Zhang, Xiaohua Li. Classification of Severely Occluded Image Sequences via Convolutional Recurrent Neural Networks [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3830

Sparse tensor recovery via N-mode FISTA with support augmentation

Paper Details

Authors:
Ashley Prater-Bennette, Lixin Shen
Submitted On:
28 November 2018 - 6:12pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

PraterBennette_GlobalSIP_1176_Presentation_v3.pdf

(93)

Subscribe

[1] Ashley Prater-Bennette, Lixin Shen, "Sparse tensor recovery via N-mode FISTA with support augmentation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3827. Accessed: Oct. 22, 2019.
@article{3827-18,
url = {http://sigport.org/3827},
author = {Ashley Prater-Bennette; Lixin Shen },
publisher = {IEEE SigPort},
title = {Sparse tensor recovery via N-mode FISTA with support augmentation},
year = {2018} }
TY - EJOUR
T1 - Sparse tensor recovery via N-mode FISTA with support augmentation
AU - Ashley Prater-Bennette; Lixin Shen
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3827
ER -
Ashley Prater-Bennette, Lixin Shen. (2018). Sparse tensor recovery via N-mode FISTA with support augmentation. IEEE SigPort. http://sigport.org/3827
Ashley Prater-Bennette, Lixin Shen, 2018. Sparse tensor recovery via N-mode FISTA with support augmentation. Available at: http://sigport.org/3827.
Ashley Prater-Bennette, Lixin Shen. (2018). "Sparse tensor recovery via N-mode FISTA with support augmentation." Web.
1. Ashley Prater-Bennette, Lixin Shen. Sparse tensor recovery via N-mode FISTA with support augmentation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3827

Sparse tensor recovery via N-mode FISTA with support augmentation

Paper Details

Authors:
Ashley Prater-Bennette, Lixin Shen
Submitted On:
28 November 2018 - 6:12pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

PraterBennette_GlobalSIP_1176_Presentation_v3.pdf

(93)

Subscribe

[1] Ashley Prater-Bennette, Lixin Shen, "Sparse tensor recovery via N-mode FISTA with support augmentation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3826. Accessed: Oct. 22, 2019.
@article{3826-18,
url = {http://sigport.org/3826},
author = {Ashley Prater-Bennette; Lixin Shen },
publisher = {IEEE SigPort},
title = {Sparse tensor recovery via N-mode FISTA with support augmentation},
year = {2018} }
TY - EJOUR
T1 - Sparse tensor recovery via N-mode FISTA with support augmentation
AU - Ashley Prater-Bennette; Lixin Shen
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3826
ER -
Ashley Prater-Bennette, Lixin Shen. (2018). Sparse tensor recovery via N-mode FISTA with support augmentation. IEEE SigPort. http://sigport.org/3826
Ashley Prater-Bennette, Lixin Shen, 2018. Sparse tensor recovery via N-mode FISTA with support augmentation. Available at: http://sigport.org/3826.
Ashley Prater-Bennette, Lixin Shen. (2018). "Sparse tensor recovery via N-mode FISTA with support augmentation." Web.
1. Ashley Prater-Bennette, Lixin Shen. Sparse tensor recovery via N-mode FISTA with support augmentation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3826

The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker


Reliable collision avoidance is one of the main requirements for autonomous driving.
Hence, it is important to correctly estimate the states of an unknown number of static and dynamic objects in real-time.
Here, data association is a major challenge for every multi-target tracker.
We propose a novel multi-target tracker called Greedy Dirichlet Process Filter (GDPF) based on the non-parametric Bayesian model called Dirichlet Processes and the fast posterior computation algorithm Sequential Updating and Greedy Search (SUGS).

Paper Details

Authors:
Patrick Burger, Hans-Joachim Wuensche
Submitted On:
27 November 2018 - 1:23pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

gdpf_presentation.zip

(65)

Subscribe

[1] Patrick Burger, Hans-Joachim Wuensche, "The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3815. Accessed: Oct. 22, 2019.
@article{3815-18,
url = {http://sigport.org/3815},
author = {Patrick Burger; Hans-Joachim Wuensche },
publisher = {IEEE SigPort},
title = {The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker},
year = {2018} }
TY - EJOUR
T1 - The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker
AU - Patrick Burger; Hans-Joachim Wuensche
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3815
ER -
Patrick Burger, Hans-Joachim Wuensche. (2018). The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker. IEEE SigPort. http://sigport.org/3815
Patrick Burger, Hans-Joachim Wuensche, 2018. The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker. Available at: http://sigport.org/3815.
Patrick Burger, Hans-Joachim Wuensche. (2018). "The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker." Web.
1. Patrick Burger, Hans-Joachim Wuensche. The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3815

Interactive Object Segmentation with Noisy Binary Inputs

Paper Details

Authors:
Gregory Canal, Sivabalan Manivasagam, Shaoheng Liang, Christopher Rozell
Submitted On:
26 November 2018 - 12:51pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Canal_globalSIP_poster.pdf

(82)

Subscribe

[1] Gregory Canal, Sivabalan Manivasagam, Shaoheng Liang, Christopher Rozell, "Interactive Object Segmentation with Noisy Binary Inputs", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3777. Accessed: Oct. 22, 2019.
@article{3777-18,
url = {http://sigport.org/3777},
author = {Gregory Canal; Sivabalan Manivasagam; Shaoheng Liang; Christopher Rozell },
publisher = {IEEE SigPort},
title = {Interactive Object Segmentation with Noisy Binary Inputs},
year = {2018} }
TY - EJOUR
T1 - Interactive Object Segmentation with Noisy Binary Inputs
AU - Gregory Canal; Sivabalan Manivasagam; Shaoheng Liang; Christopher Rozell
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3777
ER -
Gregory Canal, Sivabalan Manivasagam, Shaoheng Liang, Christopher Rozell. (2018). Interactive Object Segmentation with Noisy Binary Inputs. IEEE SigPort. http://sigport.org/3777
Gregory Canal, Sivabalan Manivasagam, Shaoheng Liang, Christopher Rozell, 2018. Interactive Object Segmentation with Noisy Binary Inputs. Available at: http://sigport.org/3777.
Gregory Canal, Sivabalan Manivasagam, Shaoheng Liang, Christopher Rozell. (2018). "Interactive Object Segmentation with Noisy Binary Inputs." Web.
1. Gregory Canal, Sivabalan Manivasagam, Shaoheng Liang, Christopher Rozell. Interactive Object Segmentation with Noisy Binary Inputs [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3777

PERFORMANCE EVALUATION OF OBJECTIVE QUALITY METRICS ON HLG-BASED HDR IMAGE CODING


We evaluate the performance of objective quality metrics for high dynamic range (HDR) image coding that uses the transfer function (TF) of the Hybrid Log-Gamma (HLG) method. Previous evaluations of objective metrics for HDR image coding have studied which of them are reliable predictors of perceived quality; however, in those tests, all the non-linear transforms used both for encoding and by the best-performing metrics are essentially very similar and based on visual perception data of detection thresholds for lightness variations.

Paper Details

Authors:
Marcelo Bertalmío
Submitted On:
29 November 2018 - 9:25pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

20181129_GlobalSIP_Yasuko.pdf

(96)

Subscribe

[1] Marcelo Bertalmío, "PERFORMANCE EVALUATION OF OBJECTIVE QUALITY METRICS ON HLG-BASED HDR IMAGE CODING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3767. Accessed: Oct. 22, 2019.
@article{3767-18,
url = {http://sigport.org/3767},
author = {Marcelo Bertalmío },
publisher = {IEEE SigPort},
title = {PERFORMANCE EVALUATION OF OBJECTIVE QUALITY METRICS ON HLG-BASED HDR IMAGE CODING},
year = {2018} }
TY - EJOUR
T1 - PERFORMANCE EVALUATION OF OBJECTIVE QUALITY METRICS ON HLG-BASED HDR IMAGE CODING
AU - Marcelo Bertalmío
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3767
ER -
Marcelo Bertalmío. (2018). PERFORMANCE EVALUATION OF OBJECTIVE QUALITY METRICS ON HLG-BASED HDR IMAGE CODING. IEEE SigPort. http://sigport.org/3767
Marcelo Bertalmío, 2018. PERFORMANCE EVALUATION OF OBJECTIVE QUALITY METRICS ON HLG-BASED HDR IMAGE CODING. Available at: http://sigport.org/3767.
Marcelo Bertalmío. (2018). "PERFORMANCE EVALUATION OF OBJECTIVE QUALITY METRICS ON HLG-BASED HDR IMAGE CODING." Web.
1. Marcelo Bertalmío. PERFORMANCE EVALUATION OF OBJECTIVE QUALITY METRICS ON HLG-BASED HDR IMAGE CODING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3767

Single image super-resolution with limited number of filters


In this paper, we propose a single image super-resolution with limited number of filters based on RAISR. RAISR is well known as rapid and accurate super-resolution method which utilizes 864 filters for upscaling. This super-resolution idea utilizes the filter learned with sufficient training set. To get low cost of calculation and comparable image quality with other highly accurate super-resolution methods, the patch of input image is classified into classes by simple hash calculation.

Paper Details

Authors:
Submitted On:
22 November 2018 - 11:51pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Single image super-resolution with limited number of filters.pptx

(64)

Subscribe

[1] , "Single image super-resolution with limited number of filters", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3733. Accessed: Oct. 22, 2019.
@article{3733-18,
url = {http://sigport.org/3733},
author = { },
publisher = {IEEE SigPort},
title = {Single image super-resolution with limited number of filters},
year = {2018} }
TY - EJOUR
T1 - Single image super-resolution with limited number of filters
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3733
ER -
. (2018). Single image super-resolution with limited number of filters. IEEE SigPort. http://sigport.org/3733
, 2018. Single image super-resolution with limited number of filters. Available at: http://sigport.org/3733.
. (2018). "Single image super-resolution with limited number of filters." Web.
1. . Single image super-resolution with limited number of filters [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3733

Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints

Paper Details

Authors:
Efstratios Kakaletsis, Olga Zoidi, Ioannis Tsingalis, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas
Submitted On:
27 March 2019 - 9:05am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints

(45)

Subscribe

[1] Efstratios Kakaletsis, Olga Zoidi, Ioannis Tsingalis, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, "Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3666. Accessed: Oct. 22, 2019.
@article{3666-18,
url = {http://sigport.org/3666},
author = {Efstratios Kakaletsis; Olga Zoidi; Ioannis Tsingalis; Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas },
publisher = {IEEE SigPort},
title = {Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints},
year = {2018} }
TY - EJOUR
T1 - Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints
AU - Efstratios Kakaletsis; Olga Zoidi; Ioannis Tsingalis; Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3666
ER -
Efstratios Kakaletsis, Olga Zoidi, Ioannis Tsingalis, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2018). Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints. IEEE SigPort. http://sigport.org/3666
Efstratios Kakaletsis, Olga Zoidi, Ioannis Tsingalis, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, 2018. Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints. Available at: http://sigport.org/3666.
Efstratios Kakaletsis, Olga Zoidi, Ioannis Tsingalis, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2018). "Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints." Web.
1. Efstratios Kakaletsis, Olga Zoidi, Ioannis Tsingalis, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. Label Propagation on Facial Images Using Similarity and Dissimilarity Labelling Constraints [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3666

Pages