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

Neural network learning (MLR-NNLR)

A MULTI-CAMERA DEEP NEURAL NETWORK FOR DETECTING ELEVATED ALERTNESS IN DRIVERS


We present a system for the detection of elevated levels of driver alertness in driver-facing video captured from multiple viewpoints. This problem is important in automotive safety as a helpful feedback signal to determine driver engagement and as a means of automatically flagging anomalous driving events. We generated a dataset of videos from 25 participants overseeing an hour each of driving sequences in a simulator consisting of a mixture of normal and near-miss driving events.

Paper Details

Authors:
John Gideon, Simon Stent, Luke Fletcher
Submitted On:
13 April 2018 - 9:57am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

poster.pdf

(144)

Subscribe

[1] John Gideon, Simon Stent, Luke Fletcher, "A MULTI-CAMERA DEEP NEURAL NETWORK FOR DETECTING ELEVATED ALERTNESS IN DRIVERS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2706. Accessed: Apr. 25, 2019.
@article{2706-18,
url = {http://sigport.org/2706},
author = {John Gideon; Simon Stent; Luke Fletcher },
publisher = {IEEE SigPort},
title = {A MULTI-CAMERA DEEP NEURAL NETWORK FOR DETECTING ELEVATED ALERTNESS IN DRIVERS},
year = {2018} }
TY - EJOUR
T1 - A MULTI-CAMERA DEEP NEURAL NETWORK FOR DETECTING ELEVATED ALERTNESS IN DRIVERS
AU - John Gideon; Simon Stent; Luke Fletcher
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2706
ER -
John Gideon, Simon Stent, Luke Fletcher. (2018). A MULTI-CAMERA DEEP NEURAL NETWORK FOR DETECTING ELEVATED ALERTNESS IN DRIVERS. IEEE SigPort. http://sigport.org/2706
John Gideon, Simon Stent, Luke Fletcher, 2018. A MULTI-CAMERA DEEP NEURAL NETWORK FOR DETECTING ELEVATED ALERTNESS IN DRIVERS. Available at: http://sigport.org/2706.
John Gideon, Simon Stent, Luke Fletcher. (2018). "A MULTI-CAMERA DEEP NEURAL NETWORK FOR DETECTING ELEVATED ALERTNESS IN DRIVERS." Web.
1. John Gideon, Simon Stent, Luke Fletcher. A MULTI-CAMERA DEEP NEURAL NETWORK FOR DETECTING ELEVATED ALERTNESS IN DRIVERS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2706

CATSEYES: Categorizing Seismic structures with tessellated scattering wavelet networks


As field seismic data sizes are dramatically increasing toward exabytes, automating the labeling of ``structural monads'' --- corresponding to geological patterns and yielding subsurface interpretation --- in a huge amount of available information would drastically reduce interpretation time. Since customary designed features may not account for gradual deformations observable in seismic data, we propose to adapt the wavelet-based scattering network methodology with a tessellation of geophysical images.

Paper Details

Authors:
Yash BHALGAT, Jean CHARLETY
Submitted On:
13 April 2018 - 9:50am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Supervised seismic structure classification clustering with wavelet scattering networks

(161)

Subscribe

[1] Yash BHALGAT, Jean CHARLETY, "CATSEYES: Categorizing Seismic structures with tessellated scattering wavelet networks", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2704. Accessed: Apr. 25, 2019.
@article{2704-18,
url = {http://sigport.org/2704},
author = {Yash BHALGAT; Jean CHARLETY },
publisher = {IEEE SigPort},
title = {CATSEYES: Categorizing Seismic structures with tessellated scattering wavelet networks},
year = {2018} }
TY - EJOUR
T1 - CATSEYES: Categorizing Seismic structures with tessellated scattering wavelet networks
AU - Yash BHALGAT; Jean CHARLETY
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2704
ER -
Yash BHALGAT, Jean CHARLETY. (2018). CATSEYES: Categorizing Seismic structures with tessellated scattering wavelet networks. IEEE SigPort. http://sigport.org/2704
Yash BHALGAT, Jean CHARLETY, 2018. CATSEYES: Categorizing Seismic structures with tessellated scattering wavelet networks. Available at: http://sigport.org/2704.
Yash BHALGAT, Jean CHARLETY. (2018). "CATSEYES: Categorizing Seismic structures with tessellated scattering wavelet networks." Web.
1. Yash BHALGAT, Jean CHARLETY. CATSEYES: Categorizing Seismic structures with tessellated scattering wavelet networks [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2704

A Large-Scale Study Of Language Models for Chord Prediction

Paper Details

Authors:
Submitted On:
13 April 2018 - 6:36am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2018.pdf

(126)

Subscribe

[1] , "A Large-Scale Study Of Language Models for Chord Prediction", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2685. Accessed: Apr. 25, 2019.
@article{2685-18,
url = {http://sigport.org/2685},
author = { },
publisher = {IEEE SigPort},
title = {A Large-Scale Study Of Language Models for Chord Prediction},
year = {2018} }
TY - EJOUR
T1 - A Large-Scale Study Of Language Models for Chord Prediction
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2685
ER -
. (2018). A Large-Scale Study Of Language Models for Chord Prediction. IEEE SigPort. http://sigport.org/2685
, 2018. A Large-Scale Study Of Language Models for Chord Prediction. Available at: http://sigport.org/2685.
. (2018). "A Large-Scale Study Of Language Models for Chord Prediction." Web.
1. . A Large-Scale Study Of Language Models for Chord Prediction [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2685

Cofnet: Predict with Confidence

Paper Details

Authors:
Tung-yu Wu, Wing H. Wong, Chen-Yi Lee
Submitted On:
13 April 2018 - 5:23am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

POSTER.pdf

(1496)

Subscribe

[1] Tung-yu Wu, Wing H. Wong, Chen-Yi Lee, "Cofnet: Predict with Confidence", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2667. Accessed: Apr. 25, 2019.
@article{2667-18,
url = {http://sigport.org/2667},
author = {Tung-yu Wu; Wing H. Wong; Chen-Yi Lee },
publisher = {IEEE SigPort},
title = {Cofnet: Predict with Confidence},
year = {2018} }
TY - EJOUR
T1 - Cofnet: Predict with Confidence
AU - Tung-yu Wu; Wing H. Wong; Chen-Yi Lee
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2667
ER -
Tung-yu Wu, Wing H. Wong, Chen-Yi Lee. (2018). Cofnet: Predict with Confidence. IEEE SigPort. http://sigport.org/2667
Tung-yu Wu, Wing H. Wong, Chen-Yi Lee, 2018. Cofnet: Predict with Confidence. Available at: http://sigport.org/2667.
Tung-yu Wu, Wing H. Wong, Chen-Yi Lee. (2018). "Cofnet: Predict with Confidence." Web.
1. Tung-yu Wu, Wing H. Wong, Chen-Yi Lee. Cofnet: Predict with Confidence [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2667

A Supervised STDP-Based Training Algorithm for Living Neural Networks


Neural networks have shown great potential in many applications like speech recognition, drug discovery, image classification, and object detection. Neural network models are inspired by biological neural networks, but they are optimized to perform machine learning tasks on digital computers.

Paper Details

Authors:
Kevin Devincentis, Yao Xiao, Zubayer Ibne Ferdous, Xiaochen Guo, Zhiyuan Yan, Yevgeny Berdichevsky
Submitted On:
13 April 2018 - 1:39am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_icassp.pdf

(1602)

Subscribe

[1] Kevin Devincentis, Yao Xiao, Zubayer Ibne Ferdous, Xiaochen Guo, Zhiyuan Yan, Yevgeny Berdichevsky, "A Supervised STDP-Based Training Algorithm for Living Neural Networks", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2611. Accessed: Apr. 25, 2019.
@article{2611-18,
url = {http://sigport.org/2611},
author = {Kevin Devincentis; Yao Xiao; Zubayer Ibne Ferdous; Xiaochen Guo; Zhiyuan Yan; Yevgeny Berdichevsky },
publisher = {IEEE SigPort},
title = {A Supervised STDP-Based Training Algorithm for Living Neural Networks},
year = {2018} }
TY - EJOUR
T1 - A Supervised STDP-Based Training Algorithm for Living Neural Networks
AU - Kevin Devincentis; Yao Xiao; Zubayer Ibne Ferdous; Xiaochen Guo; Zhiyuan Yan; Yevgeny Berdichevsky
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2611
ER -
Kevin Devincentis, Yao Xiao, Zubayer Ibne Ferdous, Xiaochen Guo, Zhiyuan Yan, Yevgeny Berdichevsky. (2018). A Supervised STDP-Based Training Algorithm for Living Neural Networks. IEEE SigPort. http://sigport.org/2611
Kevin Devincentis, Yao Xiao, Zubayer Ibne Ferdous, Xiaochen Guo, Zhiyuan Yan, Yevgeny Berdichevsky, 2018. A Supervised STDP-Based Training Algorithm for Living Neural Networks. Available at: http://sigport.org/2611.
Kevin Devincentis, Yao Xiao, Zubayer Ibne Ferdous, Xiaochen Guo, Zhiyuan Yan, Yevgeny Berdichevsky. (2018). "A Supervised STDP-Based Training Algorithm for Living Neural Networks." Web.
1. Kevin Devincentis, Yao Xiao, Zubayer Ibne Ferdous, Xiaochen Guo, Zhiyuan Yan, Yevgeny Berdichevsky. A Supervised STDP-Based Training Algorithm for Living Neural Networks [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2611

SOLVING LINEAR INVERSE PROBLEMS USING GAN PRIORS: AN ALGORITHM WITH PROVABLE GUARANTEES


In recent works, both sparsity-based methods as well as learning-based methods have proven to be successful in solving several challenging linear inverse problems. However, sparsity priors for natural signals and images suffer from poor discriminative capability, while learning-based methods seldom provide concrete theoretical guarantees. In this work, we advocate the idea of replacing hand-crafted priors, such as sparsity, with a Generative Adversarial Network (GAN) to solve linear inverse problems such as compressive sensing.

Paper Details

Authors:
Viraj Shah, Chinmay Hegde
Submitted On:
12 April 2018 - 6:24pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_icassp.pdf

(148)

Subscribe

[1] Viraj Shah, Chinmay Hegde, "SOLVING LINEAR INVERSE PROBLEMS USING GAN PRIORS: AN ALGORITHM WITH PROVABLE GUARANTEES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2511. Accessed: Apr. 25, 2019.
@article{2511-18,
url = {http://sigport.org/2511},
author = {Viraj Shah; Chinmay Hegde },
publisher = {IEEE SigPort},
title = {SOLVING LINEAR INVERSE PROBLEMS USING GAN PRIORS: AN ALGORITHM WITH PROVABLE GUARANTEES},
year = {2018} }
TY - EJOUR
T1 - SOLVING LINEAR INVERSE PROBLEMS USING GAN PRIORS: AN ALGORITHM WITH PROVABLE GUARANTEES
AU - Viraj Shah; Chinmay Hegde
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2511
ER -
Viraj Shah, Chinmay Hegde. (2018). SOLVING LINEAR INVERSE PROBLEMS USING GAN PRIORS: AN ALGORITHM WITH PROVABLE GUARANTEES. IEEE SigPort. http://sigport.org/2511
Viraj Shah, Chinmay Hegde, 2018. SOLVING LINEAR INVERSE PROBLEMS USING GAN PRIORS: AN ALGORITHM WITH PROVABLE GUARANTEES. Available at: http://sigport.org/2511.
Viraj Shah, Chinmay Hegde. (2018). "SOLVING LINEAR INVERSE PROBLEMS USING GAN PRIORS: AN ALGORITHM WITH PROVABLE GUARANTEES." Web.
1. Viraj Shah, Chinmay Hegde. SOLVING LINEAR INVERSE PROBLEMS USING GAN PRIORS: AN ALGORITHM WITH PROVABLE GUARANTEES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2511

Learning convolutional sparse coding


We propose a convolutional recurrent sparse auto-encoder
model. The model consists of a sparse encoder, which is a
convolutional extension of the learned ISTA (LISTA) method,
and a linear convolutional decoder. Our strategy offers a simple
method for learning a task-driven sparse convolutional
dictionary (CD), and producing an approximate convolutional
sparse code (CSC) over the learned dictionary. We trained
the model to minimize reconstruction loss via gradient decent
with back-propagation and have achieved competitve

Paper Details

Authors:
Hillel Sreter, Raja Giryes
Submitted On:
20 April 2018 - 12:42pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

CSC - ICASSP.pptx

(4)

CSC - ICASSP.pdf

(3)

Subscribe

[1] Hillel Sreter, Raja Giryes, "Learning convolutional sparse coding ", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2478. Accessed: Apr. 25, 2019.
@article{2478-18,
url = {http://sigport.org/2478},
author = {Hillel Sreter; Raja Giryes },
publisher = {IEEE SigPort},
title = {Learning convolutional sparse coding },
year = {2018} }
TY - EJOUR
T1 - Learning convolutional sparse coding
AU - Hillel Sreter; Raja Giryes
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2478
ER -
Hillel Sreter, Raja Giryes. (2018). Learning convolutional sparse coding . IEEE SigPort. http://sigport.org/2478
Hillel Sreter, Raja Giryes, 2018. Learning convolutional sparse coding . Available at: http://sigport.org/2478.
Hillel Sreter, Raja Giryes. (2018). "Learning convolutional sparse coding ." Web.
1. Hillel Sreter, Raja Giryes. Learning convolutional sparse coding [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2478

Document Quality Estimation using Spatial Frequency Response


The current Document Image Quality Assessment (DIQA) algorithms directly relate the Optical Character Recognition (OCR) accuracies with the quality of the document to build supervised learning frameworks. This direct correlation has two major limitations: (a) OCR may be affected by factors independent of the quality of the capture and (b) it cannot account for blur variations within an image. An alternate possibility is to quantify the quality of capture using human judgement, however, it is subjective and prone to error.

Paper Details

Authors:
Pranjal Kumar Rai, Sajal Maheshwari, Vineet Gandhi
Submitted On:
13 April 2018 - 2:24am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

rai_ICASSP.pdf

(78)

Subscribe

[1] Pranjal Kumar Rai, Sajal Maheshwari, Vineet Gandhi, "Document Quality Estimation using Spatial Frequency Response", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2469. Accessed: Apr. 25, 2019.
@article{2469-18,
url = {http://sigport.org/2469},
author = {Pranjal Kumar Rai; Sajal Maheshwari; Vineet Gandhi },
publisher = {IEEE SigPort},
title = {Document Quality Estimation using Spatial Frequency Response},
year = {2018} }
TY - EJOUR
T1 - Document Quality Estimation using Spatial Frequency Response
AU - Pranjal Kumar Rai; Sajal Maheshwari; Vineet Gandhi
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2469
ER -
Pranjal Kumar Rai, Sajal Maheshwari, Vineet Gandhi. (2018). Document Quality Estimation using Spatial Frequency Response. IEEE SigPort. http://sigport.org/2469
Pranjal Kumar Rai, Sajal Maheshwari, Vineet Gandhi, 2018. Document Quality Estimation using Spatial Frequency Response. Available at: http://sigport.org/2469.
Pranjal Kumar Rai, Sajal Maheshwari, Vineet Gandhi. (2018). "Document Quality Estimation using Spatial Frequency Response." Web.
1. Pranjal Kumar Rai, Sajal Maheshwari, Vineet Gandhi. Document Quality Estimation using Spatial Frequency Response [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2469

AUTOMATIC MOTION ARTIFACT DETECTION FOR WHOLE-BODY MAGNETIC RESONANCE IMAGING


Magnetic resonance (MR) plays an important role in medical imaging. It can be flexibly tuned towards different applications for deriving a meaningful diagnosis. However, its long acquisition times and flexible parametrization make it on the other hand prone to artifacts which obscure the underlying image content or can be misinterpreted as anatomy. Patient-induced motion artifacts are still one of the major extrinsic factors which degrade image quality.

Paper Details

Authors:
Thomas Küstner, Marvin Jandt, Annika Liebgott, Lukas Mauch, Petros Martirosian, Fabian Bamberg, Konstantin Nikolaou, Sergios Gatidis, Fritz Schick, Bin Yang
Submitted On:
12 April 2018 - 12:45pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_icassp2018.pdf

(334)

Subscribe

[1] Thomas Küstner, Marvin Jandt, Annika Liebgott, Lukas Mauch, Petros Martirosian, Fabian Bamberg, Konstantin Nikolaou, Sergios Gatidis, Fritz Schick, Bin Yang, "AUTOMATIC MOTION ARTIFACT DETECTION FOR WHOLE-BODY MAGNETIC RESONANCE IMAGING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2443. Accessed: Apr. 25, 2019.
@article{2443-18,
url = {http://sigport.org/2443},
author = {Thomas Küstner; Marvin Jandt; Annika Liebgott; Lukas Mauch; Petros Martirosian; Fabian Bamberg; Konstantin Nikolaou; Sergios Gatidis; Fritz Schick; Bin Yang },
publisher = {IEEE SigPort},
title = {AUTOMATIC MOTION ARTIFACT DETECTION FOR WHOLE-BODY MAGNETIC RESONANCE IMAGING},
year = {2018} }
TY - EJOUR
T1 - AUTOMATIC MOTION ARTIFACT DETECTION FOR WHOLE-BODY MAGNETIC RESONANCE IMAGING
AU - Thomas Küstner; Marvin Jandt; Annika Liebgott; Lukas Mauch; Petros Martirosian; Fabian Bamberg; Konstantin Nikolaou; Sergios Gatidis; Fritz Schick; Bin Yang
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2443
ER -
Thomas Küstner, Marvin Jandt, Annika Liebgott, Lukas Mauch, Petros Martirosian, Fabian Bamberg, Konstantin Nikolaou, Sergios Gatidis, Fritz Schick, Bin Yang. (2018). AUTOMATIC MOTION ARTIFACT DETECTION FOR WHOLE-BODY MAGNETIC RESONANCE IMAGING. IEEE SigPort. http://sigport.org/2443
Thomas Küstner, Marvin Jandt, Annika Liebgott, Lukas Mauch, Petros Martirosian, Fabian Bamberg, Konstantin Nikolaou, Sergios Gatidis, Fritz Schick, Bin Yang, 2018. AUTOMATIC MOTION ARTIFACT DETECTION FOR WHOLE-BODY MAGNETIC RESONANCE IMAGING. Available at: http://sigport.org/2443.
Thomas Küstner, Marvin Jandt, Annika Liebgott, Lukas Mauch, Petros Martirosian, Fabian Bamberg, Konstantin Nikolaou, Sergios Gatidis, Fritz Schick, Bin Yang. (2018). "AUTOMATIC MOTION ARTIFACT DETECTION FOR WHOLE-BODY MAGNETIC RESONANCE IMAGING." Web.
1. Thomas Küstner, Marvin Jandt, Annika Liebgott, Lukas Mauch, Petros Martirosian, Fabian Bamberg, Konstantin Nikolaou, Sergios Gatidis, Fritz Schick, Bin Yang. AUTOMATIC MOTION ARTIFACT DETECTION FOR WHOLE-BODY MAGNETIC RESONANCE IMAGING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2443

Speaker Diarization with LSTM


For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications. However, mirroring the rise of deep learning in various domains, neural network based audio embeddings, also known as d-vectors, have consistently demonstrated superior speaker verification performance. In this paper, we build on the success of d-vector based speaker verification systems to develop a new d-vector based approach to speaker diarization.

Paper Details

Authors:
Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno
Submitted On:
12 April 2018 - 11:54am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2018_poster_quan_diarization

(136)

Subscribe

[1] Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno, "Speaker Diarization with LSTM", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2421. Accessed: Apr. 25, 2019.
@article{2421-18,
url = {http://sigport.org/2421},
author = {Quan Wang; Carlton Downey; Li Wan; Philip Andrew Mansfield; Ignacio Lopez Moreno },
publisher = {IEEE SigPort},
title = {Speaker Diarization with LSTM},
year = {2018} }
TY - EJOUR
T1 - Speaker Diarization with LSTM
AU - Quan Wang; Carlton Downey; Li Wan; Philip Andrew Mansfield; Ignacio Lopez Moreno
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2421
ER -
Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno. (2018). Speaker Diarization with LSTM. IEEE SigPort. http://sigport.org/2421
Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno, 2018. Speaker Diarization with LSTM. Available at: http://sigport.org/2421.
Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno. (2018). "Speaker Diarization with LSTM." Web.
1. Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno. Speaker Diarization with LSTM [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2421

Pages