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

Deep Learning

NEURAL ADAPTIVE IMAGE DENOISER


We propose a novel neural network-based adaptive image denoiser, dubbased as Neural AIDE. Unlike other neural network-based denoisers, which typically apply supervised training to learn a mapping from a noisy patch to a clean patch, we formulate to train a neural network to learn context- based affine mappings that get applied to each noisy pixel. Our formulation enables using SURE (Stein’s Unbiased Risk Estimator)-like estimated losses of those mappings as empirical risks to minimize.

Paper Details

Authors:
Sungmin Cha, Taesup Moon
Submitted On:
14 April 2018 - 8:37am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

NAIDE_Poster_ICASSP2018

(241 downloads)

Keywords

Additional Categories

Subscribe

[1] Sungmin Cha, Taesup Moon, "NEURAL ADAPTIVE IMAGE DENOISER", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2825. Accessed: Oct. 17, 2018.
@article{2825-18,
url = {http://sigport.org/2825},
author = {Sungmin Cha; Taesup Moon },
publisher = {IEEE SigPort},
title = {NEURAL ADAPTIVE IMAGE DENOISER},
year = {2018} }
TY - EJOUR
T1 - NEURAL ADAPTIVE IMAGE DENOISER
AU - Sungmin Cha; Taesup Moon
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2825
ER -
Sungmin Cha, Taesup Moon. (2018). NEURAL ADAPTIVE IMAGE DENOISER. IEEE SigPort. http://sigport.org/2825
Sungmin Cha, Taesup Moon, 2018. NEURAL ADAPTIVE IMAGE DENOISER. Available at: http://sigport.org/2825.
Sungmin Cha, Taesup Moon. (2018). "NEURAL ADAPTIVE IMAGE DENOISER." Web.
1. Sungmin Cha, Taesup Moon. NEURAL ADAPTIVE IMAGE DENOISER [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2825

Fast Vehicle Detection with Lateral Convolutional Neural Network


Fast Vehicle Detection with Lateral Convolutional Neural Network

Paper Details

Authors:
Chen-Hang HE, Kin-Man LAM
Submitted On:
17 April 2018 - 8:58am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Lateral-CNN

(100 downloads)

Lateral-CNN Slides.pptx

(95 downloads)

Keywords

Additional Categories

Subscribe

[1] Chen-Hang HE, Kin-Man LAM, "Fast Vehicle Detection with Lateral Convolutional Neural Network", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2808. Accessed: Oct. 17, 2018.
@article{2808-18,
url = {http://sigport.org/2808},
author = {Chen-Hang HE; Kin-Man LAM },
publisher = {IEEE SigPort},
title = {Fast Vehicle Detection with Lateral Convolutional Neural Network},
year = {2018} }
TY - EJOUR
T1 - Fast Vehicle Detection with Lateral Convolutional Neural Network
AU - Chen-Hang HE; Kin-Man LAM
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2808
ER -
Chen-Hang HE, Kin-Man LAM. (2018). Fast Vehicle Detection with Lateral Convolutional Neural Network. IEEE SigPort. http://sigport.org/2808
Chen-Hang HE, Kin-Man LAM, 2018. Fast Vehicle Detection with Lateral Convolutional Neural Network. Available at: http://sigport.org/2808.
Chen-Hang HE, Kin-Man LAM. (2018). "Fast Vehicle Detection with Lateral Convolutional Neural Network." Web.
1. Chen-Hang HE, Kin-Man LAM. Fast Vehicle Detection with Lateral Convolutional Neural Network [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2808

COMPARISON OF OBJECTIVE FUNCTIONS IN CNN-BASED PROSTATE MAGNETIC RESONANCE IMAGE SEGMENTATION


We investigate the impacts of objective functions on the performance of deep-learning-based prostate magnetic resonance image segmentation. To this end, we first develop a baseline convolutional neural network (BCNN) for the prostate image segmentation, which consists of encoding, bridge, decoding, and classification modules. In the BCNN, we use 3D convolutional layers to consider volumetric information. Also, we adopt the residual feature forwarding and intermediate feature propagation techniques to make the BCNN reliably trainable for various objective functions.

Paper Details

Authors:
Juhyeok Mun, Won-Dong Jang, Deuk Jae Sung, Chang-Su Kim
Submitted On:
13 September 2017 - 10:57pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_JHMUN_POSTER.pdf

(134 downloads)

Keywords

Additional Categories

Subscribe

[1] Juhyeok Mun, Won-Dong Jang, Deuk Jae Sung, Chang-Su Kim, "COMPARISON OF OBJECTIVE FUNCTIONS IN CNN-BASED PROSTATE MAGNETIC RESONANCE IMAGE SEGMENTATION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1991. Accessed: Oct. 17, 2018.
@article{1991-17,
url = {http://sigport.org/1991},
author = {Juhyeok Mun; Won-Dong Jang; Deuk Jae Sung; Chang-Su Kim },
publisher = {IEEE SigPort},
title = {COMPARISON OF OBJECTIVE FUNCTIONS IN CNN-BASED PROSTATE MAGNETIC RESONANCE IMAGE SEGMENTATION},
year = {2017} }
TY - EJOUR
T1 - COMPARISON OF OBJECTIVE FUNCTIONS IN CNN-BASED PROSTATE MAGNETIC RESONANCE IMAGE SEGMENTATION
AU - Juhyeok Mun; Won-Dong Jang; Deuk Jae Sung; Chang-Su Kim
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1991
ER -
Juhyeok Mun, Won-Dong Jang, Deuk Jae Sung, Chang-Su Kim. (2017). COMPARISON OF OBJECTIVE FUNCTIONS IN CNN-BASED PROSTATE MAGNETIC RESONANCE IMAGE SEGMENTATION. IEEE SigPort. http://sigport.org/1991
Juhyeok Mun, Won-Dong Jang, Deuk Jae Sung, Chang-Su Kim, 2017. COMPARISON OF OBJECTIVE FUNCTIONS IN CNN-BASED PROSTATE MAGNETIC RESONANCE IMAGE SEGMENTATION. Available at: http://sigport.org/1991.
Juhyeok Mun, Won-Dong Jang, Deuk Jae Sung, Chang-Su Kim. (2017). "COMPARISON OF OBJECTIVE FUNCTIONS IN CNN-BASED PROSTATE MAGNETIC RESONANCE IMAGE SEGMENTATION." Web.
1. Juhyeok Mun, Won-Dong Jang, Deuk Jae Sung, Chang-Su Kim. COMPARISON OF OBJECTIVE FUNCTIONS IN CNN-BASED PROSTATE MAGNETIC RESONANCE IMAGE SEGMENTATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1991

VID2SPEECH: SPEECH RECONSTRUCTION FROM SILENT VIDEO


Speechreading is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible acoustic speech signal from silent video frames of a speaking person. The proposed CNN generates sound features for each frame based on its neighboring frames. Waveforms are then synthesized from the learned speech features to produce intelligible speech.

Paper Details

Authors:
Ariel Ephrat, Shmuel Peleg
Submitted On:
27 February 2017 - 3:05pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

vid2speech_poster

(228 downloads)

Subscribe

[1] Ariel Ephrat, Shmuel Peleg, "VID2SPEECH: SPEECH RECONSTRUCTION FROM SILENT VIDEO", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1448. Accessed: Oct. 17, 2018.
@article{1448-17,
url = {http://sigport.org/1448},
author = {Ariel Ephrat; Shmuel Peleg },
publisher = {IEEE SigPort},
title = {VID2SPEECH: SPEECH RECONSTRUCTION FROM SILENT VIDEO},
year = {2017} }
TY - EJOUR
T1 - VID2SPEECH: SPEECH RECONSTRUCTION FROM SILENT VIDEO
AU - Ariel Ephrat; Shmuel Peleg
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1448
ER -
Ariel Ephrat, Shmuel Peleg. (2017). VID2SPEECH: SPEECH RECONSTRUCTION FROM SILENT VIDEO. IEEE SigPort. http://sigport.org/1448
Ariel Ephrat, Shmuel Peleg, 2017. VID2SPEECH: SPEECH RECONSTRUCTION FROM SILENT VIDEO. Available at: http://sigport.org/1448.
Ariel Ephrat, Shmuel Peleg. (2017). "VID2SPEECH: SPEECH RECONSTRUCTION FROM SILENT VIDEO." Web.
1. Ariel Ephrat, Shmuel Peleg. VID2SPEECH: SPEECH RECONSTRUCTION FROM SILENT VIDEO [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1448

Recurrent SVM for Speech Recognition

Paper Details

Authors:
Shi-Xiong Zhang; Rui Zhao; Jinyu Li; Chaojun Liu; Yifan Gong
Submitted On:
19 March 2016 - 4:50am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

RecurrentSVM_poster.pdf

(308 downloads)

Subscribe

[1] Shi-Xiong Zhang; Rui Zhao; Jinyu Li; Chaojun Liu; Yifan Gong, "Recurrent SVM for Speech Recognition", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/792. Accessed: Oct. 17, 2018.
@article{792-16,
url = {http://sigport.org/792},
author = {Shi-Xiong Zhang; Rui Zhao; Jinyu Li; Chaojun Liu; Yifan Gong },
publisher = {IEEE SigPort},
title = {Recurrent SVM for Speech Recognition},
year = {2016} }
TY - EJOUR
T1 - Recurrent SVM for Speech Recognition
AU - Shi-Xiong Zhang; Rui Zhao; Jinyu Li; Chaojun Liu; Yifan Gong
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/792
ER -
Shi-Xiong Zhang; Rui Zhao; Jinyu Li; Chaojun Liu; Yifan Gong. (2016). Recurrent SVM for Speech Recognition. IEEE SigPort. http://sigport.org/792
Shi-Xiong Zhang; Rui Zhao; Jinyu Li; Chaojun Liu; Yifan Gong, 2016. Recurrent SVM for Speech Recognition. Available at: http://sigport.org/792.
Shi-Xiong Zhang; Rui Zhao; Jinyu Li; Chaojun Liu; Yifan Gong. (2016). "Recurrent SVM for Speech Recognition." Web.
1. Shi-Xiong Zhang; Rui Zhao; Jinyu Li; Chaojun Liu; Yifan Gong. Recurrent SVM for Speech Recognition [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/792