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

Image/Video Processing

Sparse Directed Graph Learning for Head Movement Prediction in 360 Video Streaming


High-definition 360 videos encoded in fine quality are typically too large in size to stream in its entirety over bandwidth (BW)-constrained networks. One popular remedy is to interactively extract and send a spatial sub-region corresponding to a viewer's current field-of-view (FoV) in a head-mounted display (HMD) for more BW-efficient streaming. Due to the non-negligible round-trip-time (RTT) delay between server and client, accurate head movement prediction that foretells a viewer's future FoVs is essential.

Paper Details

Authors:
Gene Cheung, Patrick Le Callet, Jack Z. G. Tan
Submitted On:
20 May 2020 - 7:49pm
Short Link:
Type:
Event:

Document Files

2069.pdf

(9)

Subscribe

[1] Gene Cheung, Patrick Le Callet, Jack Z. G. Tan, "Sparse Directed Graph Learning for Head Movement Prediction in 360 Video Streaming", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5420. Accessed: Jul. 03, 2020.
@article{5420-20,
url = {http://sigport.org/5420},
author = {Gene Cheung; Patrick Le Callet; Jack Z. G. Tan },
publisher = {IEEE SigPort},
title = {Sparse Directed Graph Learning for Head Movement Prediction in 360 Video Streaming},
year = {2020} }
TY - EJOUR
T1 - Sparse Directed Graph Learning for Head Movement Prediction in 360 Video Streaming
AU - Gene Cheung; Patrick Le Callet; Jack Z. G. Tan
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5420
ER -
Gene Cheung, Patrick Le Callet, Jack Z. G. Tan. (2020). Sparse Directed Graph Learning for Head Movement Prediction in 360 Video Streaming. IEEE SigPort. http://sigport.org/5420
Gene Cheung, Patrick Le Callet, Jack Z. G. Tan, 2020. Sparse Directed Graph Learning for Head Movement Prediction in 360 Video Streaming. Available at: http://sigport.org/5420.
Gene Cheung, Patrick Le Callet, Jack Z. G. Tan. (2020). "Sparse Directed Graph Learning for Head Movement Prediction in 360 Video Streaming." Web.
1. Gene Cheung, Patrick Le Callet, Jack Z. G. Tan. Sparse Directed Graph Learning for Head Movement Prediction in 360 Video Streaming [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5420

Estimation of gaze region using two dimensional probabilistic maps constructed using convolutional neural networks


Predicting the gaze of a user can have important applications in hu- man computer interactions (HCI). They find applications in areas such as social interaction, driver distraction, human robot interaction and education. Appearance based models for gaze estimation have significantly improved due to recent advances in convolutional neural network (CNN). This paper proposes a method to predict the gaze of a user with deep models purely based on CNNs.

Paper Details

Authors:
Sumit Jha, Carlos Busso
Submitted On:
20 May 2020 - 9:53am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Jha_2019-poster.pdf

(15)

Subscribe

[1] Sumit Jha, Carlos Busso, "Estimation of gaze region using two dimensional probabilistic maps constructed using convolutional neural networks", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5410. Accessed: Jul. 03, 2020.
@article{5410-20,
url = {http://sigport.org/5410},
author = {Sumit Jha; Carlos Busso },
publisher = {IEEE SigPort},
title = {Estimation of gaze region using two dimensional probabilistic maps constructed using convolutional neural networks},
year = {2020} }
TY - EJOUR
T1 - Estimation of gaze region using two dimensional probabilistic maps constructed using convolutional neural networks
AU - Sumit Jha; Carlos Busso
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5410
ER -
Sumit Jha, Carlos Busso. (2020). Estimation of gaze region using two dimensional probabilistic maps constructed using convolutional neural networks. IEEE SigPort. http://sigport.org/5410
Sumit Jha, Carlos Busso, 2020. Estimation of gaze region using two dimensional probabilistic maps constructed using convolutional neural networks. Available at: http://sigport.org/5410.
Sumit Jha, Carlos Busso. (2020). "Estimation of gaze region using two dimensional probabilistic maps constructed using convolutional neural networks." Web.
1. Sumit Jha, Carlos Busso. Estimation of gaze region using two dimensional probabilistic maps constructed using convolutional neural networks [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5410

A REAL-TIME DEEP NETWORK FOR CROWD COUNTING


Automatic analysis of highly crowded people has attracted extensive attention from computer vision research. Previous approaches for crowd counting have already achieved promising performance across various benchmarks. However, to deal with the real situation, we hope the model run as fast as possible while keeping accuracy. In this paper, we propose a compact convolutional neural network for crowd counting which learns a more efficient model with a small number of parameters.

Paper Details

Authors:
Submitted On:
19 May 2020 - 6:14am
Short Link:
Type:
Event:

Document Files

ICASSP_2020_XShi_PPT.pdf

(10)

Subscribe

[1] , "A REAL-TIME DEEP NETWORK FOR CROWD COUNTING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5399. Accessed: Jul. 03, 2020.
@article{5399-20,
url = {http://sigport.org/5399},
author = { },
publisher = {IEEE SigPort},
title = {A REAL-TIME DEEP NETWORK FOR CROWD COUNTING},
year = {2020} }
TY - EJOUR
T1 - A REAL-TIME DEEP NETWORK FOR CROWD COUNTING
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5399
ER -
. (2020). A REAL-TIME DEEP NETWORK FOR CROWD COUNTING. IEEE SigPort. http://sigport.org/5399
, 2020. A REAL-TIME DEEP NETWORK FOR CROWD COUNTING. Available at: http://sigport.org/5399.
. (2020). "A REAL-TIME DEEP NETWORK FOR CROWD COUNTING." Web.
1. . A REAL-TIME DEEP NETWORK FOR CROWD COUNTING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5399

View-angle Invariant Object Monitoring Without Image Registration


Object monitoring can be performed by change detection algorithms. However, for the image pair with a large perspective difference, the change detection performance is usually impacted by inaccurate image registration. To address the above difficulties, a novel object-specific change detection approach is proposed for object monitoring in this paper. In contrast to traditional approaches, the proposed approach is robust to view angle variation and does not require explicit image registration. Experiments demonstrate the effectiveness and advantages of the proposed approach.

Paper Details

Authors:
Xin Zhang; Chunlei Huo; Chunhong Pan
Submitted On:
19 May 2020 - 4:58am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

View-angle Invariant Object Monitoring Without Image Registration .pdf

(20)

Subscribe

[1] Xin Zhang; Chunlei Huo; Chunhong Pan, "View-angle Invariant Object Monitoring Without Image Registration ", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5398. Accessed: Jul. 03, 2020.
@article{5398-20,
url = {http://sigport.org/5398},
author = {Xin Zhang; Chunlei Huo; Chunhong Pan },
publisher = {IEEE SigPort},
title = {View-angle Invariant Object Monitoring Without Image Registration },
year = {2020} }
TY - EJOUR
T1 - View-angle Invariant Object Monitoring Without Image Registration
AU - Xin Zhang; Chunlei Huo; Chunhong Pan
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5398
ER -
Xin Zhang; Chunlei Huo; Chunhong Pan. (2020). View-angle Invariant Object Monitoring Without Image Registration . IEEE SigPort. http://sigport.org/5398
Xin Zhang; Chunlei Huo; Chunhong Pan, 2020. View-angle Invariant Object Monitoring Without Image Registration . Available at: http://sigport.org/5398.
Xin Zhang; Chunlei Huo; Chunhong Pan. (2020). "View-angle Invariant Object Monitoring Without Image Registration ." Web.
1. Xin Zhang; Chunlei Huo; Chunhong Pan. View-angle Invariant Object Monitoring Without Image Registration [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5398

BILATERAL RECURRENT NETWORK FOR SINGLE IMAGE DERAINING


Single image deraining has been widely studied in recent years. Motivated by residual learning, most deep learning based deraining approaches devote research attention to extracting rain streaks, usually yielding visual artifacts in final deraining images. To address this issue, we in this paper propose bilateral recurrent network (BRN) to simultaneously exploit rain streak layer and background image layer. Generally, we employ dual residual networks (ResNet) that are recursively unfolded to sequentially extract rain streaks and predict clean background image.

Paper Details

Authors:
Pengfei Zhu, Dongwei Ren, Hong Shi
Submitted On:
18 May 2020 - 11:23am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

BRN_slides.pdf

(12)

Subscribe

[1] Pengfei Zhu, Dongwei Ren, Hong Shi, "BILATERAL RECURRENT NETWORK FOR SINGLE IMAGE DERAINING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5393. Accessed: Jul. 03, 2020.
@article{5393-20,
url = {http://sigport.org/5393},
author = {Pengfei Zhu; Dongwei Ren; Hong Shi },
publisher = {IEEE SigPort},
title = {BILATERAL RECURRENT NETWORK FOR SINGLE IMAGE DERAINING},
year = {2020} }
TY - EJOUR
T1 - BILATERAL RECURRENT NETWORK FOR SINGLE IMAGE DERAINING
AU - Pengfei Zhu; Dongwei Ren; Hong Shi
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5393
ER -
Pengfei Zhu, Dongwei Ren, Hong Shi. (2020). BILATERAL RECURRENT NETWORK FOR SINGLE IMAGE DERAINING. IEEE SigPort. http://sigport.org/5393
Pengfei Zhu, Dongwei Ren, Hong Shi, 2020. BILATERAL RECURRENT NETWORK FOR SINGLE IMAGE DERAINING. Available at: http://sigport.org/5393.
Pengfei Zhu, Dongwei Ren, Hong Shi. (2020). "BILATERAL RECURRENT NETWORK FOR SINGLE IMAGE DERAINING." Web.
1. Pengfei Zhu, Dongwei Ren, Hong Shi. BILATERAL RECURRENT NETWORK FOR SINGLE IMAGE DERAINING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5393

JOINT ENHANCEMENT AND DENOISING OF LOW LIGHT IMAGES VIA JND TRANSFORM


Low light images suffer from low dynamic range and severe noise due to low signal-to-noise ratio (SNR). In this paper, we propose joint enhancement and denoising of low light images via justnoticeable-difference (JND) transform. We achieve contrast enhancement and noise reduction simultaneously based on human visual perception. First, we perform contrast enhancement based on perceptual histogram to effectively allocate a dynamic range while preventing over-enhancement. Second, we generate JND map based on an HVS response model from foreground and background luminance, called JND transform.

Paper Details

Authors:
Long Yu, Haonan Su, Cheolkon Jung
Submitted On:
16 May 2020 - 6:14am
Short Link:
Type:
Event:

Document Files

ICASSP_2020.ppt

(23)

Subscribe

[1] Long Yu, Haonan Su, Cheolkon Jung, "JOINT ENHANCEMENT AND DENOISING OF LOW LIGHT IMAGES VIA JND TRANSFORM", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5371. Accessed: Jul. 03, 2020.
@article{5371-20,
url = {http://sigport.org/5371},
author = {Long Yu; Haonan Su; Cheolkon Jung },
publisher = {IEEE SigPort},
title = {JOINT ENHANCEMENT AND DENOISING OF LOW LIGHT IMAGES VIA JND TRANSFORM},
year = {2020} }
TY - EJOUR
T1 - JOINT ENHANCEMENT AND DENOISING OF LOW LIGHT IMAGES VIA JND TRANSFORM
AU - Long Yu; Haonan Su; Cheolkon Jung
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5371
ER -
Long Yu, Haonan Su, Cheolkon Jung. (2020). JOINT ENHANCEMENT AND DENOISING OF LOW LIGHT IMAGES VIA JND TRANSFORM. IEEE SigPort. http://sigport.org/5371
Long Yu, Haonan Su, Cheolkon Jung, 2020. JOINT ENHANCEMENT AND DENOISING OF LOW LIGHT IMAGES VIA JND TRANSFORM. Available at: http://sigport.org/5371.
Long Yu, Haonan Su, Cheolkon Jung. (2020). "JOINT ENHANCEMENT AND DENOISING OF LOW LIGHT IMAGES VIA JND TRANSFORM." Web.
1. Long Yu, Haonan Su, Cheolkon Jung. JOINT ENHANCEMENT AND DENOISING OF LOW LIGHT IMAGES VIA JND TRANSFORM [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5371

Look globally, age locally: Face aging with an attention mechanism


Face aging is of great importance for cross-age recognition and entertainment-related applications. Recently, conditional generative adversarial networks (cGANs) have achieved impressive results for facial aging. Existing cGANs-based methods usually require a pixel-wise loss to keep the identity and background consistent. However, minimizing the pixel-wise loss between the input and synthesized images likely resulting in a ghosted or blurry face.

Paper Details

Authors:
Submitted On:
15 May 2020 - 9:17pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

slide_paper5430.pdf

(19)

Subscribe

[1] , "Look globally, age locally: Face aging with an attention mechanism", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5362. Accessed: Jul. 03, 2020.
@article{5362-20,
url = {http://sigport.org/5362},
author = { },
publisher = {IEEE SigPort},
title = {Look globally, age locally: Face aging with an attention mechanism},
year = {2020} }
TY - EJOUR
T1 - Look globally, age locally: Face aging with an attention mechanism
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5362
ER -
. (2020). Look globally, age locally: Face aging with an attention mechanism. IEEE SigPort. http://sigport.org/5362
, 2020. Look globally, age locally: Face aging with an attention mechanism. Available at: http://sigport.org/5362.
. (2020). "Look globally, age locally: Face aging with an attention mechanism." Web.
1. . Look globally, age locally: Face aging with an attention mechanism [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5362

Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising


While convolutional neural nets (CNN) have achieved remarkable performance for a wide range of inverse imaging applications, the filter coefficients are computed in a purely data-driven manner and are not explainable. Inspired by an analytically derived CNN by Hadji et al., in this paper we construct a new layered graph convolutional neural net (GCNN) using GraphBio as our graph filter.

Paper Details

Authors:
, Gene Cheung, Richard Wildes and Chia-Wen Lin
Submitted On:
15 May 2020 - 8:51pm
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

Icassp_DeepAGF_2020_slides

(28)

Subscribe

[1] , Gene Cheung, Richard Wildes and Chia-Wen Lin, "Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5361. Accessed: Jul. 03, 2020.
@article{5361-20,
url = {http://sigport.org/5361},
author = {; Gene Cheung; Richard Wildes and Chia-Wen Lin },
publisher = {IEEE SigPort},
title = {Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising},
year = {2020} }
TY - EJOUR
T1 - Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising
AU - ; Gene Cheung; Richard Wildes and Chia-Wen Lin
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5361
ER -
, Gene Cheung, Richard Wildes and Chia-Wen Lin. (2020). Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising. IEEE SigPort. http://sigport.org/5361
, Gene Cheung, Richard Wildes and Chia-Wen Lin, 2020. Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising. Available at: http://sigport.org/5361.
, Gene Cheung, Richard Wildes and Chia-Wen Lin. (2020). "Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising." Web.
1. , Gene Cheung, Richard Wildes and Chia-Wen Lin. Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5361

Mr Nikolajs Skuratovs


In this paper we consider the problem of recovering a signal x of size N from noisy and compressed measurements y = A x + w of size M, where the measurement matrix A is right-orthogonally invariant (ROI). Vector Approximate Message Passing (VAMP) demonstrates great reconstruction results for even highly ill-conditioned matrices A in relatively few iterations. However, performing each iteration is challenging due to either computational or memory point of view.

Paper Details

Authors:
Nikolajs Skuratovs, Michael Davies
Submitted On:
15 May 2020 - 7:04pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_presentation_v2_pdf.pdf

(17)

Subscribe

[1] Nikolajs Skuratovs, Michael Davies, "Mr Nikolajs Skuratovs", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5359. Accessed: Jul. 03, 2020.
@article{5359-20,
url = {http://sigport.org/5359},
author = {Nikolajs Skuratovs; Michael Davies },
publisher = {IEEE SigPort},
title = {Mr Nikolajs Skuratovs},
year = {2020} }
TY - EJOUR
T1 - Mr Nikolajs Skuratovs
AU - Nikolajs Skuratovs; Michael Davies
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5359
ER -
Nikolajs Skuratovs, Michael Davies. (2020). Mr Nikolajs Skuratovs. IEEE SigPort. http://sigport.org/5359
Nikolajs Skuratovs, Michael Davies, 2020. Mr Nikolajs Skuratovs. Available at: http://sigport.org/5359.
Nikolajs Skuratovs, Michael Davies. (2020). "Mr Nikolajs Skuratovs." Web.
1. Nikolajs Skuratovs, Michael Davies. Mr Nikolajs Skuratovs [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5359

Video-Driven Speech Reconstruction - Show & Tell Demo


This demo will showcase our video-to-audio model which attempts to reconstruct speech from short videos of spoken statements. Our model does so in a completely end-to-end manner where raw audio is generated based on the input video. This approach bypasses the need for separate lip-reading and text-to-speech models. The advantage of such an approach is that it does not require large transcribed datasets and it is not based on intermediate representations like text which remove any intonation and emotional content from the speech.

Paper Details

Authors:
Konstantinos Vougioukas, Stavros Petridis, Björn Schuller, Maja Pantic
Submitted On:
15 May 2020 - 11:55am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Video-driven Speech Reconstruction using Generative Adversarial Networks Show & Tell Demo.pdf

(33)

Subscribe

[1] Konstantinos Vougioukas, Stavros Petridis, Björn Schuller, Maja Pantic, "Video-Driven Speech Reconstruction - Show & Tell Demo", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5351. Accessed: Jul. 03, 2020.
@article{5351-20,
url = {http://sigport.org/5351},
author = {Konstantinos Vougioukas; Stavros Petridis; Björn Schuller; Maja Pantic },
publisher = {IEEE SigPort},
title = {Video-Driven Speech Reconstruction - Show & Tell Demo},
year = {2020} }
TY - EJOUR
T1 - Video-Driven Speech Reconstruction - Show & Tell Demo
AU - Konstantinos Vougioukas; Stavros Petridis; Björn Schuller; Maja Pantic
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5351
ER -
Konstantinos Vougioukas, Stavros Petridis, Björn Schuller, Maja Pantic. (2020). Video-Driven Speech Reconstruction - Show & Tell Demo. IEEE SigPort. http://sigport.org/5351
Konstantinos Vougioukas, Stavros Petridis, Björn Schuller, Maja Pantic, 2020. Video-Driven Speech Reconstruction - Show & Tell Demo. Available at: http://sigport.org/5351.
Konstantinos Vougioukas, Stavros Petridis, Björn Schuller, Maja Pantic. (2020). "Video-Driven Speech Reconstruction - Show & Tell Demo." Web.
1. Konstantinos Vougioukas, Stavros Petridis, Björn Schuller, Maja Pantic. Video-Driven Speech Reconstruction - Show & Tell Demo [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5351

Pages