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

Image/Video Coding

DISCRIMINATIVE SALIENCY-POSE-ATTENTION COVARIANCE FOR ACTION RECOGNITION


Most covariance-based representations of actions are focused on the statistical features of poses by empirical averaging weighting. Note that these poses have a variety of saliency levels for different actions. Neglecting pose saliency could degrade the discriminative power of the covariance features, and further reduce the performance of action recognition. In this paper, we propose a novel saliency weighting covariance feature representation, Saliency-Pose-Attention Covariance(SPA-Cov), which reduces the negative effects from the ambiguous pose samples.

Paper Details

Authors:
Zhiyong Feng,Yong Su,Meng Xing
Submitted On:
18 February 2019 - 6:34am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster for conference.

Subscribe

[1] Zhiyong Feng,Yong Su,Meng Xing, "DISCRIMINATIVE SALIENCY-POSE-ATTENTION COVARIANCE FOR ACTION RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3854. Accessed: Mar. 19, 2019.
@article{3854-19,
url = {http://sigport.org/3854},
author = {Zhiyong Feng;Yong Su;Meng Xing },
publisher = {IEEE SigPort},
title = {DISCRIMINATIVE SALIENCY-POSE-ATTENTION COVARIANCE FOR ACTION RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - DISCRIMINATIVE SALIENCY-POSE-ATTENTION COVARIANCE FOR ACTION RECOGNITION
AU - Zhiyong Feng;Yong Su;Meng Xing
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3854
ER -
Zhiyong Feng,Yong Su,Meng Xing. (2019). DISCRIMINATIVE SALIENCY-POSE-ATTENTION COVARIANCE FOR ACTION RECOGNITION. IEEE SigPort. http://sigport.org/3854
Zhiyong Feng,Yong Su,Meng Xing, 2019. DISCRIMINATIVE SALIENCY-POSE-ATTENTION COVARIANCE FOR ACTION RECOGNITION. Available at: http://sigport.org/3854.
Zhiyong Feng,Yong Su,Meng Xing. (2019). "DISCRIMINATIVE SALIENCY-POSE-ATTENTION COVARIANCE FOR ACTION RECOGNITION." Web.
1. Zhiyong Feng,Yong Su,Meng Xing. DISCRIMINATIVE SALIENCY-POSE-ATTENTION COVARIANCE FOR ACTION RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3854

A RETINA-INSPIRED ENCODER: AN INNOVATIVE STEP ON IMAGE CODING USING LEAKY INTEGRATE-AND-FIRE NEURONS

Paper Details

Authors:
Melpomeni Dimopoulou, Effrosyni Doutsi, Marc Antonini
Submitted On:
9 October 2018 - 4:13pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_2018.pdf

Subscribe

[1] Melpomeni Dimopoulou, Effrosyni Doutsi, Marc Antonini, "A RETINA-INSPIRED ENCODER: AN INNOVATIVE STEP ON IMAGE CODING USING LEAKY INTEGRATE-AND-FIRE NEURONS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3642. Accessed: Mar. 19, 2019.
@article{3642-18,
url = {http://sigport.org/3642},
author = {Melpomeni Dimopoulou; Effrosyni Doutsi; Marc Antonini },
publisher = {IEEE SigPort},
title = {A RETINA-INSPIRED ENCODER: AN INNOVATIVE STEP ON IMAGE CODING USING LEAKY INTEGRATE-AND-FIRE NEURONS},
year = {2018} }
TY - EJOUR
T1 - A RETINA-INSPIRED ENCODER: AN INNOVATIVE STEP ON IMAGE CODING USING LEAKY INTEGRATE-AND-FIRE NEURONS
AU - Melpomeni Dimopoulou; Effrosyni Doutsi; Marc Antonini
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3642
ER -
Melpomeni Dimopoulou, Effrosyni Doutsi, Marc Antonini. (2018). A RETINA-INSPIRED ENCODER: AN INNOVATIVE STEP ON IMAGE CODING USING LEAKY INTEGRATE-AND-FIRE NEURONS. IEEE SigPort. http://sigport.org/3642
Melpomeni Dimopoulou, Effrosyni Doutsi, Marc Antonini, 2018. A RETINA-INSPIRED ENCODER: AN INNOVATIVE STEP ON IMAGE CODING USING LEAKY INTEGRATE-AND-FIRE NEURONS. Available at: http://sigport.org/3642.
Melpomeni Dimopoulou, Effrosyni Doutsi, Marc Antonini. (2018). "A RETINA-INSPIRED ENCODER: AN INNOVATIVE STEP ON IMAGE CODING USING LEAKY INTEGRATE-AND-FIRE NEURONS." Web.
1. Melpomeni Dimopoulou, Effrosyni Doutsi, Marc Antonini. A RETINA-INSPIRED ENCODER: AN INNOVATIVE STEP ON IMAGE CODING USING LEAKY INTEGRATE-AND-FIRE NEURONS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3642

A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding

Paper Details

Authors:
Submitted On:
8 October 2018 - 2:50am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

A machine learning approach to accurate sequence-level rate control scheme for video coding.1.1.pdf

Subscribe

[1] , "A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3611. Accessed: Mar. 19, 2019.
@article{3611-18,
url = {http://sigport.org/3611},
author = { },
publisher = {IEEE SigPort},
title = {A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding},
year = {2018} }
TY - EJOUR
T1 - A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3611
ER -
. (2018). A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding. IEEE SigPort. http://sigport.org/3611
, 2018. A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding. Available at: http://sigport.org/3611.
. (2018). "A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding." Web.
1. . A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3611

SYMMETRY-BASED GRAPH FOURIER TRANSFORMS FOR IMAGE REPRESENTATION


It is well-known that the application of the Discrete Cosine Transform
(DCT) in transform coding schemes is justified by the fact that
it belongs to a family of transforms asymptotically equivalent to the
Karhunen-Loève Transform (KLT) of a first order Markov process.
However, when the pixel-to-pixel correlation is low the DCT does
not provide a compression performance comparable with the KLT.
In this paper, we propose a set of symmetry-based Graph Fourier
Transforms (GFT) whose associated graphs present a totally or partially

Paper Details

Authors:
Alessandro Gnutti, Fabrizio Guerrini, Riccardo Leonardi, Antonio Ortega
Submitted On:
5 October 2018 - 12:37pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster ICIP18_v3.pdf

Subscribe

[1] Alessandro Gnutti, Fabrizio Guerrini, Riccardo Leonardi, Antonio Ortega, "SYMMETRY-BASED GRAPH FOURIER TRANSFORMS FOR IMAGE REPRESENTATION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3547. Accessed: Mar. 19, 2019.
@article{3547-18,
url = {http://sigport.org/3547},
author = {Alessandro Gnutti; Fabrizio Guerrini; Riccardo Leonardi; Antonio Ortega },
publisher = {IEEE SigPort},
title = {SYMMETRY-BASED GRAPH FOURIER TRANSFORMS FOR IMAGE REPRESENTATION},
year = {2018} }
TY - EJOUR
T1 - SYMMETRY-BASED GRAPH FOURIER TRANSFORMS FOR IMAGE REPRESENTATION
AU - Alessandro Gnutti; Fabrizio Guerrini; Riccardo Leonardi; Antonio Ortega
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3547
ER -
Alessandro Gnutti, Fabrizio Guerrini, Riccardo Leonardi, Antonio Ortega. (2018). SYMMETRY-BASED GRAPH FOURIER TRANSFORMS FOR IMAGE REPRESENTATION. IEEE SigPort. http://sigport.org/3547
Alessandro Gnutti, Fabrizio Guerrini, Riccardo Leonardi, Antonio Ortega, 2018. SYMMETRY-BASED GRAPH FOURIER TRANSFORMS FOR IMAGE REPRESENTATION. Available at: http://sigport.org/3547.
Alessandro Gnutti, Fabrizio Guerrini, Riccardo Leonardi, Antonio Ortega. (2018). "SYMMETRY-BASED GRAPH FOURIER TRANSFORMS FOR IMAGE REPRESENTATION." Web.
1. Alessandro Gnutti, Fabrizio Guerrini, Riccardo Leonardi, Antonio Ortega. SYMMETRY-BASED GRAPH FOURIER TRANSFORMS FOR IMAGE REPRESENTATION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3547

Rate-Distortion Theory for Affine Global Motion Compensation in Video Coding


In this work, we derive the rate-distortion function for video coding using affine global motion compensation.
We model the displacement estimation error during motion estimation and obtain the bit rate after applying the rate-distortion theory.
We assume that the displacement estimation error is caused by a perturbed affine transformation.
The 6 affine transformation parameters are assumed statistically independent, with each of them having a zero-mean Gaussian distributed estimation error.

Paper Details

Authors:
Holger Meuel, Stephan Ferenz, Yiqun Liu, Jörn Ostermann
Submitted On:
16 October 2018 - 4:45am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Meuel_et_al_Rate-Distortion_Theory_for_Affine_Global_Motion_Compensation_in_Video_Coding_ICIP2018_POSTER.pdf

Keywords

Additional Categories

Subscribe

[1] Holger Meuel, Stephan Ferenz, Yiqun Liu, Jörn Ostermann, "Rate-Distortion Theory for Affine Global Motion Compensation in Video Coding", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3532. Accessed: Mar. 19, 2019.
@article{3532-18,
url = {http://sigport.org/3532},
author = {Holger Meuel; Stephan Ferenz; Yiqun Liu; Jörn Ostermann },
publisher = {IEEE SigPort},
title = {Rate-Distortion Theory for Affine Global Motion Compensation in Video Coding},
year = {2018} }
TY - EJOUR
T1 - Rate-Distortion Theory for Affine Global Motion Compensation in Video Coding
AU - Holger Meuel; Stephan Ferenz; Yiqun Liu; Jörn Ostermann
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3532
ER -
Holger Meuel, Stephan Ferenz, Yiqun Liu, Jörn Ostermann. (2018). Rate-Distortion Theory for Affine Global Motion Compensation in Video Coding. IEEE SigPort. http://sigport.org/3532
Holger Meuel, Stephan Ferenz, Yiqun Liu, Jörn Ostermann, 2018. Rate-Distortion Theory for Affine Global Motion Compensation in Video Coding. Available at: http://sigport.org/3532.
Holger Meuel, Stephan Ferenz, Yiqun Liu, Jörn Ostermann. (2018). "Rate-Distortion Theory for Affine Global Motion Compensation in Video Coding." Web.
1. Holger Meuel, Stephan Ferenz, Yiqun Liu, Jörn Ostermann. Rate-Distortion Theory for Affine Global Motion Compensation in Video Coding [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3532

A FAST HEURISTIC FOR TILE PARTITIONING AND PROCESSOR ASSIGNMENT IN HEVC


As the compression efficiency of HEVC comes at the cost of high complexity, especially in the encoder’s side, improved parallelization techniques that will speedup the encoding process are essential. One of the parallelization granules offered by HEVC is the tile level, whereby a frame is split into a grid like fashion with each resulting rectangular area (tile) being independently encoded. While tile parallelism has attracted research interest, the primary focus was to characterize performance and develop load balancing schemes assuming a one on one tile processor assignment.

Paper Details

Authors:
Panos K. Papadopoulos, Maria Koziri, Thanasis Loukopoulos
Submitted On:
5 October 2018 - 6:21am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Papadopoulos_icip18

Subscribe

[1] Panos K. Papadopoulos, Maria Koziri, Thanasis Loukopoulos, "A FAST HEURISTIC FOR TILE PARTITIONING AND PROCESSOR ASSIGNMENT IN HEVC", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3531. Accessed: Mar. 19, 2019.
@article{3531-18,
url = {http://sigport.org/3531},
author = {Panos K. Papadopoulos; Maria Koziri; Thanasis Loukopoulos },
publisher = {IEEE SigPort},
title = {A FAST HEURISTIC FOR TILE PARTITIONING AND PROCESSOR ASSIGNMENT IN HEVC},
year = {2018} }
TY - EJOUR
T1 - A FAST HEURISTIC FOR TILE PARTITIONING AND PROCESSOR ASSIGNMENT IN HEVC
AU - Panos K. Papadopoulos; Maria Koziri; Thanasis Loukopoulos
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3531
ER -
Panos K. Papadopoulos, Maria Koziri, Thanasis Loukopoulos. (2018). A FAST HEURISTIC FOR TILE PARTITIONING AND PROCESSOR ASSIGNMENT IN HEVC. IEEE SigPort. http://sigport.org/3531
Panos K. Papadopoulos, Maria Koziri, Thanasis Loukopoulos, 2018. A FAST HEURISTIC FOR TILE PARTITIONING AND PROCESSOR ASSIGNMENT IN HEVC. Available at: http://sigport.org/3531.
Panos K. Papadopoulos, Maria Koziri, Thanasis Loukopoulos. (2018). "A FAST HEURISTIC FOR TILE PARTITIONING AND PROCESSOR ASSIGNMENT IN HEVC." Web.
1. Panos K. Papadopoulos, Maria Koziri, Thanasis Loukopoulos. A FAST HEURISTIC FOR TILE PARTITIONING AND PROCESSOR ASSIGNMENT IN HEVC [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3531

Accurate Dictionary Learning with Direct Sparsity Control


Dictionary learning is a popular method for obtaining sparse linear representations for high dimensional data, with many applications in image classification, signal processing and machine learning.

Paper Details

Authors:
Hongyu Mou, Adrian Barbu
Submitted On:
5 October 2018 - 6:03am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster

Subscribe

[1] Hongyu Mou, Adrian Barbu, "Accurate Dictionary Learning with Direct Sparsity Control", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3529. Accessed: Mar. 19, 2019.
@article{3529-18,
url = {http://sigport.org/3529},
author = {Hongyu Mou; Adrian Barbu },
publisher = {IEEE SigPort},
title = {Accurate Dictionary Learning with Direct Sparsity Control},
year = {2018} }
TY - EJOUR
T1 - Accurate Dictionary Learning with Direct Sparsity Control
AU - Hongyu Mou; Adrian Barbu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3529
ER -
Hongyu Mou, Adrian Barbu. (2018). Accurate Dictionary Learning with Direct Sparsity Control. IEEE SigPort. http://sigport.org/3529
Hongyu Mou, Adrian Barbu, 2018. Accurate Dictionary Learning with Direct Sparsity Control. Available at: http://sigport.org/3529.
Hongyu Mou, Adrian Barbu. (2018). "Accurate Dictionary Learning with Direct Sparsity Control." Web.
1. Hongyu Mou, Adrian Barbu. Accurate Dictionary Learning with Direct Sparsity Control [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3529

Regularized Gradient Descent Training of Steered Mixture of Experts for Sparse Image Representation


The Steered Mixture-of-Experts (SMoE) framework targets a sparse space-continuous representation for images, videos, and light fields enabling processing tasks such as approximation, denoising, and coding.
The underlying stochastic processes are represented by a Gaussian Mixture Model, traditionally trained by the Expectation-Maximization (EM) algorithm.
We instead propose to use the MSE of the regressed imagery for a Gradient Descent optimization as primary training objective.

Paper Details

Authors:
Erik Bochinski, Rolf Jongebloed, Michael Tok, Thomas Sikora
Submitted On:
5 October 2018 - 3:27am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip18_poster.pdf

Subscribe

[1] Erik Bochinski, Rolf Jongebloed, Michael Tok, Thomas Sikora, "Regularized Gradient Descent Training of Steered Mixture of Experts for Sparse Image Representation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3510. Accessed: Mar. 19, 2019.
@article{3510-18,
url = {http://sigport.org/3510},
author = {Erik Bochinski; Rolf Jongebloed; Michael Tok; Thomas Sikora },
publisher = {IEEE SigPort},
title = {Regularized Gradient Descent Training of Steered Mixture of Experts for Sparse Image Representation},
year = {2018} }
TY - EJOUR
T1 - Regularized Gradient Descent Training of Steered Mixture of Experts for Sparse Image Representation
AU - Erik Bochinski; Rolf Jongebloed; Michael Tok; Thomas Sikora
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3510
ER -
Erik Bochinski, Rolf Jongebloed, Michael Tok, Thomas Sikora. (2018). Regularized Gradient Descent Training of Steered Mixture of Experts for Sparse Image Representation. IEEE SigPort. http://sigport.org/3510
Erik Bochinski, Rolf Jongebloed, Michael Tok, Thomas Sikora, 2018. Regularized Gradient Descent Training of Steered Mixture of Experts for Sparse Image Representation. Available at: http://sigport.org/3510.
Erik Bochinski, Rolf Jongebloed, Michael Tok, Thomas Sikora. (2018). "Regularized Gradient Descent Training of Steered Mixture of Experts for Sparse Image Representation." Web.
1. Erik Bochinski, Rolf Jongebloed, Michael Tok, Thomas Sikora. Regularized Gradient Descent Training of Steered Mixture of Experts for Sparse Image Representation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3510

SCALABLE LIGHT FIELD CODING USING WEIGHTED BINARY IMAGES


We propose an efficient coding scheme for a dense light field, i.e.,
a set of multi-viewpoint images taken with very small viewpoint intervals.
The key idea behind our proposal is that a light field is represented
only using weighted binary images, where several binary
images and corresponding weight values are to be chosen to optimally
approximate the light field. The coding scheme derived from
this idea is completely different from those of modern image/video
coding standards. However, we found that our scheme can achieve

Paper Details

Authors:
Keita Takahashi, Toshiaki Fujii
Submitted On:
5 October 2018 - 3:21am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Light-field, Scalable coding

Subscribe

[1] Keita Takahashi, Toshiaki Fujii, "SCALABLE LIGHT FIELD CODING USING WEIGHTED BINARY IMAGES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3509. Accessed: Mar. 19, 2019.
@article{3509-18,
url = {http://sigport.org/3509},
author = {Keita Takahashi; Toshiaki Fujii },
publisher = {IEEE SigPort},
title = {SCALABLE LIGHT FIELD CODING USING WEIGHTED BINARY IMAGES},
year = {2018} }
TY - EJOUR
T1 - SCALABLE LIGHT FIELD CODING USING WEIGHTED BINARY IMAGES
AU - Keita Takahashi; Toshiaki Fujii
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3509
ER -
Keita Takahashi, Toshiaki Fujii. (2018). SCALABLE LIGHT FIELD CODING USING WEIGHTED BINARY IMAGES. IEEE SigPort. http://sigport.org/3509
Keita Takahashi, Toshiaki Fujii, 2018. SCALABLE LIGHT FIELD CODING USING WEIGHTED BINARY IMAGES. Available at: http://sigport.org/3509.
Keita Takahashi, Toshiaki Fujii. (2018). "SCALABLE LIGHT FIELD CODING USING WEIGHTED BINARY IMAGES." Web.
1. Keita Takahashi, Toshiaki Fujii. SCALABLE LIGHT FIELD CODING USING WEIGHTED BINARY IMAGES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3509

Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation

Paper Details

Authors:
Submitted On:
4 October 2018 - 8:14pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster of Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation

Subscribe

[1] , "Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3471. Accessed: Mar. 19, 2019.
@article{3471-18,
url = {http://sigport.org/3471},
author = { },
publisher = {IEEE SigPort},
title = {Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation},
year = {2018} }
TY - EJOUR
T1 - Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3471
ER -
. (2018). Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation. IEEE SigPort. http://sigport.org/3471
, 2018. Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation. Available at: http://sigport.org/3471.
. (2018). "Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation." Web.
1. . Rate Control Optimization of x265 Using Information From Quarter-Resolution Pre-Motion-Estimation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3471

Pages