Signal Processing - November 2017 - 23

ICIP 2016 Competition on Mobile
Ocular Biometric Recognition
Rattani, A.; Derakhshani, R.;
Saripalle, S.K; Gottemukkula, V.
The aim of this competition is to evaluate and compare the performance of
mobile ocular biometric recognition
schemes in visible light on a large
scale database (VISOB Data Set ICIP
2016 Challenge Version) using standard evaluation methods. Four different teams from universities across the
world participated in this competition,
submitting five algorithms altogether.
The best results were obtained by a
team from Norwegian Biometrics Laboratory (NTNU, Norway).

2016

Semantic Context and DepthAware Object Proposal Generation
Zhang, H.; He, X.; Porikli, F.; Kneip, L.
This paper presents a context-aware
object proposal generation method for
stereo images. The authors propose to
incorporate additional geometric and

PANEL AND FORUM

high-level semantic context information into the proposal generation.
2016

Super-Resolution of Compressed
Videos Using Convolutional
Neural Networks
Kappeler, A.; Yoo, S.; Dai, Q.;
Katsaggelos, A.K.
In this paper, for the problem of compressed video superresolution, the
authors propose a CNN that is trained on
both the spatial and the temporal di--men-
sions of compressed videos to enhance
their spatial resolution. Consecutive
frames are motion compensated and used
as input to a CNN that provides superresolved video frames as output.
2016

Classification of Hyperspectral
Image Based on Deep Belief
Networks
Li, T.; Zhang, J.; Zhang, Y.
In this paper, deep-learning frameworks,
the restricted Boltzmann machine

model, and its deep structure deep belief
networks are introduced in hyperspectral image processing as the feature
extraction and classification approach.

2014

Image Character Recognition
Using Deep Convolutional Neural
Network Learned from
Different Languages
Bai, J.; Chen, Z.; Feng, B.; Xu, B.
This paper proposes a shared-hiddenlayer deep convolutional neural network (SHL-CNN) for image character
recognition. In SHL-CNN, the hidden
layers are made common across characters from different languages, performing a universal feature extraction
process that aims at learning common
character traits existing in different
languages, such as strokes, while the
final softmax layer is made language
dependent, trained based on characters
from the destination language only.
2014
SP


(continued from page 13)

Steve Young (sjy@eng.cam.ac.uk) is
a professor of information engineering at
the University of Cambridge, United
Kingdom, and a senior member of technical staff at Apple. His main research interests lie in the area of statistical spoken
language systems, including speech
recognition, speech synthesis, and dialog
management. He is the recipient of a
number of awards including an IEEE
Signal Processing Society Technical
Achievement Award and the IEEE James
L. Flanagan Speech and Audio Pro-
cessing Award. He is a Fellow of the
IEEE and the U.K. Royal Academy of
Engineering. In addition to his academic
career, he has also founded a number of
successful start-ups in the speech technology area.

References

[1] L. Deng and D. Yu, "Deep learning: Methods and
applications," in Foundations and Trends in Signal
Processing Series. Boston, MA: NOW Publishers, 2014.
[2] I. Goodfellow, Y. Bengio, and A. Courville, Deep
Learning. Cambridge, MA: MIT Press, 2016.
[3] L. Deng and X. Li, "Machine learning paradigms
for speech recognition: An overview," IEEE Trans.
Audio, Speech, Lang. Process., vol. 21, pp. 1060-
1089, May 2013.
[4] D. I. Shuman, S. K. Narang, P. Frossard, A.
Ortega, and P. Vandergheynst, "The emerging field
of signal processing on graphs: Extending high
dimensional data analysis to networks and other irregular domains," IEEE Signal Process. Mag., vol. 30,
pp. 83-98, May 2013.
[5] A. Sandryhaila and J. M. F. Moura, "Big data processing with signal processing on graphs," IEEE Signal
Process. Mag., vol. 31, no. 5, pp. 80-90, Sept. 2014.
[6] S. Chen, R. Varma, A. Sandryhaila, and J.
Kovacˇevic´, "Discrete signal processing on graphs:
Sampling theory," IEEE Trans. Signal Process., vol.
63, no. 24, pp. 6510-6523, Dec. 2015.
[7] F.-L. Luo and C. Zhang, Eds. Signal Processing
for 5G: Algor ith m s a n d Im plem en ta t io ns .
Chichester, U.K.: Wiley-IEEE Press, 2016.

IEEE SIGNAL PROCESSING MAGAZINE

|

November 2017

|

[8] R. Collobert, J. Weston, L. Bottou, M. Karlen, K.
Kavukcuoglu, and P. Kuksa, "Natural language processing (almost) from scratch," J. Mach. Learn. Res.,
vol. 12, pp. 2493-2537, Aug. 2011.
[9] L. Deng, "Industrial technology advances: Deep
learning: From speech recognition to language and
multimodal processing," APSIPA Trans. Signal
Inform. Process., vol. 5, pp. 1-15, Jan. 2016.
[10] N. Mrksic, I. Vulic, D. O. Seaghdha, I. Leviant,
R. Reichart, M. Gasic, A. Korhonen, and S. Young,
"Semantic specialization of distributional word vector
spaces using monolingual and cross-lingual constraints," Trans. Assoc. Computat. Linguistics, vol. 5,
pp. 309-324, Sept. 2017.
[11] J. A. Fessler. (2017). Medical image reconstruction: A brief overview of past milestones and future
directions. [Online]. Available: http://arxiv.org/
abs/1707.05927
[12] Y. Liu, J. Chen, and L. Deng, "Unsupervised
sequence classification using sequential output statistics," in Proc. NIPS, Dec. 2017.
[13] G. Hinton, et al., "Deep neural networks for
acoustic modeling in speech recognition," IEEE
Signal Process. Mag., vol. 29, no. 6, pp. 82-97, Nov.
2012.


SP

23
http://www.arxiv.org/
Table of Contents for the Digital Edition of Signal Processing - November 2017
