Home People Research Publications Demos
         
News Jobs Prospective
Students
About Internal

Yeong Jun Koh

Department of Electrical and Computer Engineering
University of California, San Diego

9500 Gilman Drive,
EBU-1, Room 4607
La Jolla, CA 92093-0409

yjkoh at eng.ucsd.edu
Phone: (858)344-7604


Brief Biography

I am currently a Post-doc at Statistical Visual Computing Lab, Department of Electrical and Computer Engineering at University of California, San Diego (UCSD), under the supervision of Prof. Nuno Vasconcelos. I received the B.S. degree and the Ph.D. degree in electrical engineering from Korea University, Seoul, South Korea, in 2011 and 2018, respectively.

Research

My researh interests are computer vision and machine laerning, espeically in the problems of video object discovery and segmentation.

Publications

My online publication profile can be found at Google Scholar.

Sequential Clique Optimization for Video Object Segmentation,
Yeong Jun Koh, Young-Yoon Lee, and Chang-Su Kim
European Conference on Computer Vision (ECCV)
Munich, Germany, 2018

Multiscale Feature Extractors for Stereo Matching Cost Computation
Kyung-rae Kim, Yeong Jun Koh, and Chang-Su Kim
IEEE Acess
vol. 6, pp. 27971-27983, May, 2018.

Unsupervised Primary Object Discovery in Videos Based on Evolutionary Primary Object Modeling with Reliable Object Proposals
Yeong Jun Koh and Chang-Su Kim
IEEE Transactions on Image Processing (TIP)
vol. 26, no. 11, pp. 5203{5216, Nov. 2017

CDTS: Collaborative Detection, Tracking, and Segmentation for Online Multiple Object Segmentation in Videos
Yeong Jun Koh and Chang-Su Kim
IEEE International Conference on Computer Vision (ICCV)
Venice, Italy, Oct. 2017

Primary Object Segmentation in Videos Based on Region Augmentation and Reduction
Yeong Jun Koh and Chang-Su Kim
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)
Honolulu, HI, Jul. 2017

POD: Discovering Primary Objects in Videos Based on Evolutionary Refinement of Object Recurrence, Background, and Primary Object Models,
Yeong Jun Koh, Won-Dong Jang, and Chang-Su Kim
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)
Las Vegas, NV, Jun. 2016

Video Stabilization Based on Feature Trajectory Augmentation and Selection and Robust Mesh Grid Warping
Yeong Jun Koh, Chulwoo Lee, and Chang-Su Kim
IEEE Transactions on Image Processing (TIP)
vol. 24, no. 12, pp. 5260{5273, Dec. 2015

Dark Image Enhancement Based on Pairwise Target Contrast and Multi-scale Detail Boosting
Youngbae Kim, Yeong Jun Koh, Chulwoo Lee, Sehoon Kim, and Chang-Su Kim
IEEE International Conference on Image Processing (ICIP)
Quebec, Canada, Sep. 2015

Robust Video Stabilization Based on Mesh Grid Warping of Rolling-free Features
Yeong Jun Koh, Jae-Young Sim, and Chang-Su Kim
IEEE International Conference on Image Processing (ICIP)
Paris, France, Oct. 2014

Efficient Fine-granular Scalable Coding of 3D Mesh Sequences
Jae-Kyun Ahn, Yeong Jun Koh, and Chang-Su Kim
IEEE Transactions on Multimedia (TMM)
vol. 15, no. 3, pp. 485-497, Apr. 2013

Professional Experience

Statistical Visual Computing Lab, UC San Diego
Postdoctoral Scholar-Employee, 2018-present

Media Communications Lab, Korea University
Graduate Student Researcher, 2011-2018





© SVCL