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

Multimedia Signal Processing

Convolutional Neural Network based Fast Intra Mode Prediction for H.266/FVC Video Coding

Paper Details

Authors:
Ting-Lan Lin, Kai-Wen Liang, Jing-Ya Huang, Yu-Liang Tu, and Pao-Chi Chang
Submitted On:
31 March 2020 - 6:06am
Short Link:
Type:
Event:

Document Files

Convolutional Neural Network based Fast Intra Mode Prediction.pdf

(3)

Subscribe

[1] Ting-Lan Lin, Kai-Wen Liang, Jing-Ya Huang, Yu-Liang Tu, and Pao-Chi Chang, "Convolutional Neural Network based Fast Intra Mode Prediction for H.266/FVC Video Coding", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5079. Accessed: Apr. 04, 2020.
@article{5079-20,
url = {http://sigport.org/5079},
author = {Ting-Lan Lin; Kai-Wen Liang; Jing-Ya Huang; Yu-Liang Tu; and Pao-Chi Chang },
publisher = {IEEE SigPort},
title = {Convolutional Neural Network based Fast Intra Mode Prediction for H.266/FVC Video Coding},
year = {2020} }
TY - EJOUR
T1 - Convolutional Neural Network based Fast Intra Mode Prediction for H.266/FVC Video Coding
AU - Ting-Lan Lin; Kai-Wen Liang; Jing-Ya Huang; Yu-Liang Tu; and Pao-Chi Chang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5079
ER -
Ting-Lan Lin, Kai-Wen Liang, Jing-Ya Huang, Yu-Liang Tu, and Pao-Chi Chang. (2020). Convolutional Neural Network based Fast Intra Mode Prediction for H.266/FVC Video Coding. IEEE SigPort. http://sigport.org/5079
Ting-Lan Lin, Kai-Wen Liang, Jing-Ya Huang, Yu-Liang Tu, and Pao-Chi Chang, 2020. Convolutional Neural Network based Fast Intra Mode Prediction for H.266/FVC Video Coding. Available at: http://sigport.org/5079.
Ting-Lan Lin, Kai-Wen Liang, Jing-Ya Huang, Yu-Liang Tu, and Pao-Chi Chang. (2020). "Convolutional Neural Network based Fast Intra Mode Prediction for H.266/FVC Video Coding." Web.
1. Ting-Lan Lin, Kai-Wen Liang, Jing-Ya Huang, Yu-Liang Tu, and Pao-Chi Chang. Convolutional Neural Network based Fast Intra Mode Prediction for H.266/FVC Video Coding [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5079

Multimodal active speaker detection and virtual cinematography for video conferencing


Active speaker detection (ASD) and virtual cinematography (VC) can significantly improve the remote user experience of a video conference by automatically panning, tilting and zooming of a video conferencing camera: users subjectively rate an expert video cinematographer’s video significantly higher than unedited video. We describe a new automated ASD and VC that performs within 0.3 MOS of an expert cinematographer based on subjective ratings with a 1-5 scale.

Paper Details

Authors:
Ross Cutler, Ramin Mehran, Sam Johnson, Cha Zhang, Adam Kirk, Oliver Whyte, Adarsh Kowdle
Submitted On:
12 February 2020 - 12:55am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP 2020 ASD.pdf

(21)

Subscribe

[1] Ross Cutler, Ramin Mehran, Sam Johnson, Cha Zhang, Adam Kirk, Oliver Whyte, Adarsh Kowdle, "Multimodal active speaker detection and virtual cinematography for video conferencing", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4980. Accessed: Apr. 04, 2020.
@article{4980-20,
url = {http://sigport.org/4980},
author = {Ross Cutler; Ramin Mehran; Sam Johnson; Cha Zhang; Adam Kirk; Oliver Whyte; Adarsh Kowdle },
publisher = {IEEE SigPort},
title = {Multimodal active speaker detection and virtual cinematography for video conferencing},
year = {2020} }
TY - EJOUR
T1 - Multimodal active speaker detection and virtual cinematography for video conferencing
AU - Ross Cutler; Ramin Mehran; Sam Johnson; Cha Zhang; Adam Kirk; Oliver Whyte; Adarsh Kowdle
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4980
ER -
Ross Cutler, Ramin Mehran, Sam Johnson, Cha Zhang, Adam Kirk, Oliver Whyte, Adarsh Kowdle. (2020). Multimodal active speaker detection and virtual cinematography for video conferencing. IEEE SigPort. http://sigport.org/4980
Ross Cutler, Ramin Mehran, Sam Johnson, Cha Zhang, Adam Kirk, Oliver Whyte, Adarsh Kowdle, 2020. Multimodal active speaker detection and virtual cinematography for video conferencing. Available at: http://sigport.org/4980.
Ross Cutler, Ramin Mehran, Sam Johnson, Cha Zhang, Adam Kirk, Oliver Whyte, Adarsh Kowdle. (2020). "Multimodal active speaker detection and virtual cinematography for video conferencing." Web.
1. Ross Cutler, Ramin Mehran, Sam Johnson, Cha Zhang, Adam Kirk, Oliver Whyte, Adarsh Kowdle. Multimodal active speaker detection and virtual cinematography for video conferencing [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4980

A Fast Iterative Method for Removing Sparse Noise from Sparse Signals


Reconstructing a signal corrupted by impulsive noise is of high importance in several applications, including impulsive noise removal from images, audios and videos, and separating texts from images. Investigating this problem, in this paper we propose a new method to reconstruct a noise-corrupted signal where both signal and noise are sparse but in different domains. We apply our algorithm for impulsive noise (Salt-and-Pepper Noise (SPN) and Random-Valued Impulsive Noise (RVIN) removal from images and compare our results with other notable algorithms in the literature.

Paper Details

Authors:
nematollah zarmehi, farokh marvasti, saeed gazor
Submitted On:
7 November 2019 - 3:48pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Sahar Sadrizadeh.pdf

(52)

Subscribe

[1] nematollah zarmehi, farokh marvasti, saeed gazor, "A Fast Iterative Method for Removing Sparse Noise from Sparse Signals", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4926. Accessed: Apr. 04, 2020.
@article{4926-19,
url = {http://sigport.org/4926},
author = {nematollah zarmehi; farokh marvasti; saeed gazor },
publisher = {IEEE SigPort},
title = {A Fast Iterative Method for Removing Sparse Noise from Sparse Signals},
year = {2019} }
TY - EJOUR
T1 - A Fast Iterative Method for Removing Sparse Noise from Sparse Signals
AU - nematollah zarmehi; farokh marvasti; saeed gazor
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4926
ER -
nematollah zarmehi, farokh marvasti, saeed gazor. (2019). A Fast Iterative Method for Removing Sparse Noise from Sparse Signals. IEEE SigPort. http://sigport.org/4926
nematollah zarmehi, farokh marvasti, saeed gazor, 2019. A Fast Iterative Method for Removing Sparse Noise from Sparse Signals. Available at: http://sigport.org/4926.
nematollah zarmehi, farokh marvasti, saeed gazor. (2019). "A Fast Iterative Method for Removing Sparse Noise from Sparse Signals." Web.
1. nematollah zarmehi, farokh marvasti, saeed gazor. A Fast Iterative Method for Removing Sparse Noise from Sparse Signals [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4926

Dynamic Guidance For Depth Map Restoration

Paper Details

Authors:
Submitted On:
23 September 2019 - 9:03am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

Dynamic Guidance For Depth Map Restoration-RanZhu(paper id 80).pdf

(57)

Subscribe

[1] , "Dynamic Guidance For Depth Map Restoration", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4821. Accessed: Apr. 04, 2020.
@article{4821-19,
url = {http://sigport.org/4821},
author = { },
publisher = {IEEE SigPort},
title = {Dynamic Guidance For Depth Map Restoration},
year = {2019} }
TY - EJOUR
T1 - Dynamic Guidance For Depth Map Restoration
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4821
ER -
. (2019). Dynamic Guidance For Depth Map Restoration. IEEE SigPort. http://sigport.org/4821
, 2019. Dynamic Guidance For Depth Map Restoration. Available at: http://sigport.org/4821.
. (2019). "Dynamic Guidance For Depth Map Restoration." Web.
1. . Dynamic Guidance For Depth Map Restoration [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4821

RATE-DISTORTION DRIVEN SEPARATION OF DIFFUSE AND SPECULAR COMPONENTS IN MULTIVIEW IMAGERY


In this work we explore an overcomplete representation of
multiview imagery for the purpose of compression. We
present a rate-distortion (R-D) driven approach to decompose
multiview datasets into two additive parts which can
be interpreted as being the diffuse and specular components.
We apply different transforms to each component such that
the compressibility of input data is improved. We describe
a framework which performs the R-D optimized separation
in a registered domain to avoid the complexity of warping

Paper Details

Authors:
Maryam Haghighat, Reji Mathew and David Taubman
Submitted On:
21 September 2019 - 7:18am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019_Haghighat_Poster.pdf

(63)

Subscribe

[1] Maryam Haghighat, Reji Mathew and David Taubman, "RATE-DISTORTION DRIVEN SEPARATION OF DIFFUSE AND SPECULAR COMPONENTS IN MULTIVIEW IMAGERY", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4805. Accessed: Apr. 04, 2020.
@article{4805-19,
url = {http://sigport.org/4805},
author = {Maryam Haghighat; Reji Mathew and David Taubman },
publisher = {IEEE SigPort},
title = {RATE-DISTORTION DRIVEN SEPARATION OF DIFFUSE AND SPECULAR COMPONENTS IN MULTIVIEW IMAGERY},
year = {2019} }
TY - EJOUR
T1 - RATE-DISTORTION DRIVEN SEPARATION OF DIFFUSE AND SPECULAR COMPONENTS IN MULTIVIEW IMAGERY
AU - Maryam Haghighat; Reji Mathew and David Taubman
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4805
ER -
Maryam Haghighat, Reji Mathew and David Taubman. (2019). RATE-DISTORTION DRIVEN SEPARATION OF DIFFUSE AND SPECULAR COMPONENTS IN MULTIVIEW IMAGERY. IEEE SigPort. http://sigport.org/4805
Maryam Haghighat, Reji Mathew and David Taubman, 2019. RATE-DISTORTION DRIVEN SEPARATION OF DIFFUSE AND SPECULAR COMPONENTS IN MULTIVIEW IMAGERY. Available at: http://sigport.org/4805.
Maryam Haghighat, Reji Mathew and David Taubman. (2019). "RATE-DISTORTION DRIVEN SEPARATION OF DIFFUSE AND SPECULAR COMPONENTS IN MULTIVIEW IMAGERY." Web.
1. Maryam Haghighat, Reji Mathew and David Taubman. RATE-DISTORTION DRIVEN SEPARATION OF DIFFUSE AND SPECULAR COMPONENTS IN MULTIVIEW IMAGERY [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4805

Influence of viewpoint on visual saliency models for volumetric content


In order to predict where humans look in a 3D immersive en- vironment, saliency can be computed using either 3D saliency models or view-based approaches (2D projection). In fact, building a 3D complete model is still a challenging task that is not investigated enough in the research field while 2D imag- ing approaches have been extensively studied and have shown solid performances.

Paper Details

Authors:
Mona Abid, Matthieu Perreira Da Silva, Patrick Le Callet
Submitted On:
20 September 2019 - 3:59am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Lecture_ICIP_2019.pdf

(42)

Keywords

Additional Categories

Subscribe

[1] Mona Abid, Matthieu Perreira Da Silva, Patrick Le Callet, " Influence of viewpoint on visual saliency models for volumetric content", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4763. Accessed: Apr. 04, 2020.
@article{4763-19,
url = {http://sigport.org/4763},
author = {Mona Abid; Matthieu Perreira Da Silva; Patrick Le Callet },
publisher = {IEEE SigPort},
title = { Influence of viewpoint on visual saliency models for volumetric content},
year = {2019} }
TY - EJOUR
T1 - Influence of viewpoint on visual saliency models for volumetric content
AU - Mona Abid; Matthieu Perreira Da Silva; Patrick Le Callet
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4763
ER -
Mona Abid, Matthieu Perreira Da Silva, Patrick Le Callet. (2019). Influence of viewpoint on visual saliency models for volumetric content. IEEE SigPort. http://sigport.org/4763
Mona Abid, Matthieu Perreira Da Silva, Patrick Le Callet, 2019. Influence of viewpoint on visual saliency models for volumetric content. Available at: http://sigport.org/4763.
Mona Abid, Matthieu Perreira Da Silva, Patrick Le Callet. (2019). " Influence of viewpoint on visual saliency models for volumetric content." Web.
1. Mona Abid, Matthieu Perreira Da Silva, Patrick Le Callet. Influence of viewpoint on visual saliency models for volumetric content [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4763

HAND GRAPH REPRESENTATIONS FOR UNSUPERVISED SEGMENTATION OF COMPLEX ACTIVITIES


Analysis of hand skeleton data can be used to understand patterns in manipulation and assembly tasks. This paper introduces a graphbased representation of hand skeleton data and proposes a method to perform unsupervised temporal segmentation of a sequence of subtasks in order to evaluate the efficiency of an assembly task. We explore the properties of different choices of hand graphs and their spectral decomposition. A comparative performance of these graphs is presented in the context of complex activity segmentation.

Paper Details

Authors:
Jiun-Yu Kao, Antonio Ortega, Tomoya Sawada, Hassan Mansour, Anthony Vetro, Akira Minezawa
Submitted On:
10 May 2019 - 1:50pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSPposter2019_PratyushaDas.pdf

(62)

Subscribe

[1] Jiun-Yu Kao, Antonio Ortega, Tomoya Sawada, Hassan Mansour, Anthony Vetro, Akira Minezawa, "HAND GRAPH REPRESENTATIONS FOR UNSUPERVISED SEGMENTATION OF COMPLEX ACTIVITIES", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4381. Accessed: Apr. 04, 2020.
@article{4381-19,
url = {http://sigport.org/4381},
author = {Jiun-Yu Kao; Antonio Ortega; Tomoya Sawada; Hassan Mansour; Anthony Vetro; Akira Minezawa },
publisher = {IEEE SigPort},
title = {HAND GRAPH REPRESENTATIONS FOR UNSUPERVISED SEGMENTATION OF COMPLEX ACTIVITIES},
year = {2019} }
TY - EJOUR
T1 - HAND GRAPH REPRESENTATIONS FOR UNSUPERVISED SEGMENTATION OF COMPLEX ACTIVITIES
AU - Jiun-Yu Kao; Antonio Ortega; Tomoya Sawada; Hassan Mansour; Anthony Vetro; Akira Minezawa
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4381
ER -
Jiun-Yu Kao, Antonio Ortega, Tomoya Sawada, Hassan Mansour, Anthony Vetro, Akira Minezawa. (2019). HAND GRAPH REPRESENTATIONS FOR UNSUPERVISED SEGMENTATION OF COMPLEX ACTIVITIES. IEEE SigPort. http://sigport.org/4381
Jiun-Yu Kao, Antonio Ortega, Tomoya Sawada, Hassan Mansour, Anthony Vetro, Akira Minezawa, 2019. HAND GRAPH REPRESENTATIONS FOR UNSUPERVISED SEGMENTATION OF COMPLEX ACTIVITIES. Available at: http://sigport.org/4381.
Jiun-Yu Kao, Antonio Ortega, Tomoya Sawada, Hassan Mansour, Anthony Vetro, Akira Minezawa. (2019). "HAND GRAPH REPRESENTATIONS FOR UNSUPERVISED SEGMENTATION OF COMPLEX ACTIVITIES." Web.
1. Jiun-Yu Kao, Antonio Ortega, Tomoya Sawada, Hassan Mansour, Anthony Vetro, Akira Minezawa. HAND GRAPH REPRESENTATIONS FOR UNSUPERVISED SEGMENTATION OF COMPLEX ACTIVITIES [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4381

RESIDUAL SIGNALS MODELING FOR LAYERED IMAGE/VIDEO SOFTCAST WITH HYBRID DIGITAL-ANALOG TRANSMISSION

Paper Details

Authors:
Jing Zhao; Jiyu Xie; Ruiqin Xiong
Submitted On:
7 October 2018 - 10:53pm
Short Link:
Type:
Event:

Document Files

Poster_RESIDUAL_SIGNALS_MODELING_FOR_LAYERED_ SOFTCAST_WITH_HYBRID_DIGITAL-ANALOG_TRANSMISSION.pdf

(77)

Subscribe

[1] Jing Zhao; Jiyu Xie; Ruiqin Xiong, " RESIDUAL SIGNALS MODELING FOR LAYERED IMAGE/VIDEO SOFTCAST WITH HYBRID DIGITAL-ANALOG TRANSMISSION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3605. Accessed: Apr. 04, 2020.
@article{3605-18,
url = {http://sigport.org/3605},
author = {Jing Zhao; Jiyu Xie; Ruiqin Xiong },
publisher = {IEEE SigPort},
title = { RESIDUAL SIGNALS MODELING FOR LAYERED IMAGE/VIDEO SOFTCAST WITH HYBRID DIGITAL-ANALOG TRANSMISSION},
year = {2018} }
TY - EJOUR
T1 - RESIDUAL SIGNALS MODELING FOR LAYERED IMAGE/VIDEO SOFTCAST WITH HYBRID DIGITAL-ANALOG TRANSMISSION
AU - Jing Zhao; Jiyu Xie; Ruiqin Xiong
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3605
ER -
Jing Zhao; Jiyu Xie; Ruiqin Xiong. (2018). RESIDUAL SIGNALS MODELING FOR LAYERED IMAGE/VIDEO SOFTCAST WITH HYBRID DIGITAL-ANALOG TRANSMISSION. IEEE SigPort. http://sigport.org/3605
Jing Zhao; Jiyu Xie; Ruiqin Xiong, 2018. RESIDUAL SIGNALS MODELING FOR LAYERED IMAGE/VIDEO SOFTCAST WITH HYBRID DIGITAL-ANALOG TRANSMISSION. Available at: http://sigport.org/3605.
Jing Zhao; Jiyu Xie; Ruiqin Xiong. (2018). " RESIDUAL SIGNALS MODELING FOR LAYERED IMAGE/VIDEO SOFTCAST WITH HYBRID DIGITAL-ANALOG TRANSMISSION." Web.
1. Jing Zhao; Jiyu Xie; Ruiqin Xiong. RESIDUAL SIGNALS MODELING FOR LAYERED IMAGE/VIDEO SOFTCAST WITH HYBRID DIGITAL-ANALOG TRANSMISSION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3605

Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework

Paper Details

Authors:
Submitted On:
15 April 2018 - 12:22pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP_3200.pdf

(256)

Subscribe

[1] , "Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2898. Accessed: Apr. 04, 2020.
@article{2898-18,
url = {http://sigport.org/2898},
author = { },
publisher = {IEEE SigPort},
title = {Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework},
year = {2018} }
TY - EJOUR
T1 - Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2898
ER -
. (2018). Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework. IEEE SigPort. http://sigport.org/2898
, 2018. Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework. Available at: http://sigport.org/2898.
. (2018). "Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework." Web.
1. . Scene Image Classification using ReducedVirtual Feature Representation in Sparse Framework [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2898

Demonstration of Rapid Frequency Selective Reconstruction for Image Resolution Enhancement

Paper Details

Authors:
Nils Genser, Jürgen Seiler, Markus Jonscher, André Kaup
Submitted On:
15 September 2017 - 4:29am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

poster_landscape.pdf

(315)

Subscribe

[1] Nils Genser, Jürgen Seiler, Markus Jonscher, André Kaup, "Demonstration of Rapid Frequency Selective Reconstruction for Image Resolution Enhancement", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2108. Accessed: Apr. 04, 2020.
@article{2108-17,
url = {http://sigport.org/2108},
author = {Nils Genser; Jürgen Seiler; Markus Jonscher; André Kaup },
publisher = {IEEE SigPort},
title = {Demonstration of Rapid Frequency Selective Reconstruction for Image Resolution Enhancement},
year = {2017} }
TY - EJOUR
T1 - Demonstration of Rapid Frequency Selective Reconstruction for Image Resolution Enhancement
AU - Nils Genser; Jürgen Seiler; Markus Jonscher; André Kaup
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2108
ER -
Nils Genser, Jürgen Seiler, Markus Jonscher, André Kaup. (2017). Demonstration of Rapid Frequency Selective Reconstruction for Image Resolution Enhancement. IEEE SigPort. http://sigport.org/2108
Nils Genser, Jürgen Seiler, Markus Jonscher, André Kaup, 2017. Demonstration of Rapid Frequency Selective Reconstruction for Image Resolution Enhancement. Available at: http://sigport.org/2108.
Nils Genser, Jürgen Seiler, Markus Jonscher, André Kaup. (2017). "Demonstration of Rapid Frequency Selective Reconstruction for Image Resolution Enhancement." Web.
1. Nils Genser, Jürgen Seiler, Markus Jonscher, André Kaup. Demonstration of Rapid Frequency Selective Reconstruction for Image Resolution Enhancement [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2108

Pages