Junseok Kwon

Ph.D. Student


Computer Vision Lab.
Ph.D. Student
School of Electrical Engineering and Computer Sciences
Seoul National University
Email: s98parad(at) gmail.com, paradis0(at) snu.ac.kr
Curriculum Vitae (CV)












News

I'll be a post-doctoral researcher at Computer Vision Lab, ETH Zurich.


Major Interests

- Object tracking
- Visual surveillance
- Monte Carlo Sampling method and its variants


Educations

2008.3 ~ 2013.2: Doctor's course in School of Electrical Engineering and Computer Science, Seoul National University, Seoul, Korea.
2006.3 ~ 2008.2 : Master's course in School of Electrical Engineering and Computer Science, Seoul National University, Seoul, Korea.
1998.3 ~ 2006.2 : B.S. in School of Electrical Engineering, Seoul National University, Seoul, Korea.


Reviewer

Journal: TPAMI, TIP, TMM, TCSVT, IVC
Conference: CVPR (2012~2013), ICCV (2011, 2013), ECCV (2012), ACCV (2010, 2012)


Publications
< Journal publications >

- Tracking by Sampling and Integrating Multiple Trackers
Junseok Kwon, and Kyoung Mu Lee, IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), In revision

- Highly Non-Rigid Object Tracking via Patch-based Dynamic Appearance Modeling
Junseok Kwon, and Kyoung Mu Lee, IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), Accepted for publication, 2013.
[pdf]

- Wang-Landau Monte Carlo-based Tracking Methods for Abrupt Motions
Junseok Kwon, and Kyoung Mu Lee, IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), VOL. 35, NO. 4, APRIL. 2013
[pdf] [project page]

< Conference publications >

- Minimum Uncertainty Gap for Robust Visual Tracking
Junseok Kwon, and Kyoung Mu Lee, The 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, USA. 2013.
[pdf]

- Robust Visual Tracking using Autoregressive Hidden Markov Model
Dong Woo Park, Junseok Kwon, and Kyoung Mu Lee, The 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, USA. 2012.
[pdf]

- A Unified Framework for Event Summarization and Rare Event Detection
Junseok Kwon, and Kyoung Mu Lee, The 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, USA. 2012.
[pdf]

- Tracking by Sampling Trackers
Junseok Kwon, and Kyoung Mu Lee, The 13th IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain. 2011.
(Oral presentation, 3.7% acceptance rate)
[project page]

- Visual Tracking Decomposition
Junseok Kwon, and Kyoung Mu Lee, The 23th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, USA. 2010.
(Oral presentation, 4.5% acceptance rate)
[project page]

- Simultaneous Video Synchronization and Rare Event Detection via Cross-EntropyMonte Carlo Optimization
Junseok Kwon, and Kyoung Mu Lee, The 12th IEEE International Conference on Computer Vision (ICCV) Workshop, Kyoto, Japan. 2009.
(Oral presentation)
[pdf]

- Tracking of a Non-Rigid Object via Patch-based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo Sampling
Junseok Kwon, and Kyoung Mu Lee, The 22th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, USA. 2009.
[project page]

- Tracking of Abrupt Motion using Wang-Landau Monte Carlo Estimation
Junseok Kwon, and Kyoung Mu Lee, The 10th European Conference on Computer Vision (ECCV), Marseille, France. 2008.
[project page]




Awards

2012.11 11th ACCV Best Reviewers
2012.6 25th CVPR Doctoral Consortium
2012.2 18th Samsung Humantech Thesis Prize : Bronze Prize
2011.2 23th Image Processing and Image Understanding : Best Poster
2011.2 17th Samsung Humantech Thesis Prize : Gold Prize
2010.2 16th Samsung Humantech Thesis Prize : Honor Prize


Patents

Junseok Kwon and Kyoung Mu Lee. KOR Patent 1011077360000, Method for tracking object on visual (January, 2012)


Projects

2011.09 ~ 2012.06 : Event reasoning and summarization in surveillance videos, Microsoft Research Asia
2009.12 ~ 2010.11 : Model based people detection and tracking, LG Electronics
2008.05 ~ 2009.04 : IR based object detection, Samsung Thales

SNU Computer Vision Lab logo