Home People Research Publications Demos
News Jobs Prospective
About Internal

Sunhyoung Han

Department of Electrical and Computer Engineering,
University of California, San Diego
9500 Gilman Drive, Mail code 0409
EBU 1, Room 5512
La Jolla, CA 92093-0409

s h a n @ i d a n a l y t i c s . c o m
Phone: (858) 534-4538

I am now a PhD student in Statistical Visual Computing Lab, ECE department, UCSD. I received my B.S. and M.S. from VLSI & CAD Lab, Department of Electrical Engineering, Yonsei University, Seoul, Korea, in 1998 and 2000. During the year 2000 and 2004 I worked in Hynix Electronics and LetsVision Corp., Seoul, Korea. I joined to UCSD in 2004.


My research interests are computer vision, machine learning and computational modeling. My current research focus on developing biologically inspired computational vision model for various object recognition problems.

Feedforward saliency network with trainable neuron model We investigate the biological plausibility of statistical inference and learning, tuned to the statistics of natural images. It is shown that a rich family of statistical decision rules, confidence measures and risk estimates can be implemented with the computations to the standard neurophysiological model of V1. This is used to augment object recognition networks with top-down saliency.     

Amorphous object detection in the wild A discriminant saliency network is applied to the problem of amorphous object detection. Amorphous objects are defined as objects without distinctive edge or shape structure.     

Image compression using Object-based Regions of Interest Learning ROI masks for image and video coding.     

Top-down discriminant saliency Top-down discriminant saliency is defined with respect to a one-vs-all classification. The optimal discriminant saliency detector is derived and applied to the problem of learning from weakly-supervised examples.     

  Biologically Plausible Detection of Amorphous Objects in the Wild
Sunhyoung Han and Nuno Vasconcelos,
IEEE CVPR Workshop on Biologically-Consistent Vision,
pp. 17-24, June 2011.

?IEEE [ps][pdf]
  Biologically Plausible Saliency Mechanisms Improve Feedforward Object Recognition
Sunhyoung Han and Nuno Vasconcelos
Vision Research, vol. 50(22), 2295-2307, October 2010
[pdf] [doi:10.1016/j.visres.2010.05.034]
  Discriminant saliency, the detection of suspicious coincidences, and applications to visual recognition
Dashan Gao, Sunhyoung Han and Nuno Vasconcelos,
IEEE Transactions on Pattern Analysis and Machine Intelligence,
vol. 31(6), pp. 989-1005, June 2009.

?IEEE [ps][pdf] [doi:10.1109/TPAMI.2009.27]
  Complex discriminant features for object classification
Sunhyoung Han and Nuno Vasconcelos,
International Conference on Image Processing (ICIP),
Oct. 2008. [GOT BEST PAPER award]
[ps] [pdf]
  Object-based regions of interest for image compression
Sunhyoung Han and Nuno Vasconcelos,
Data Compression Conference (DCC), pp 132-141
Snowbird, Utah, Mar. 2008.
[ps] [pdf]
  Image Compression using Object-based Regions of Interest
Sunhyoung Han and Nuno Vasconcelos,
International Conference on Image Processing (ICIP), pp. 3097-3100
Atlanta, Georgia, Oct. 2006.
[ps] [pdf]