Seunghoon Hong
Postdoctoral Fellow

Computer Science & Engineering Division
University of Michigan
Ann Arbor, MI, USA

Contact: 3920 Beyster Building, 2260 Hayward Street, Ann Arbor, MI, 48109
Email : hongseu [at] umich [dot] edu

[Google Scholar] [Github]

Short Bio

I am a postdoctoral fellow at EECS department, University of Michigan. I am working with Professor Honglak Lee on topics related to deep learning and its application to computer vision. Before joining Umich, I received my Ph.D. degree at the Dept. of Computer Science and Engineering, POSTECH, Korea under the supervision of Professor Bohyung Han. My research interests include machine learning and computer vision with particular interests in weakly supervised learning and interpretable machine learning.

News

Publications

 

Weakly Supervised Learning with Deep Convolutional Neural Networks for Semantic Segmentation:
Understanding Semantic Layout of Images with Minimum Human Supervision

Seunghoon Hong, Suha Kwak, Bohyung Han
In Signal Processing Magazine 2017
[pdf]


 

Weakly Supervised Semantic Segmentation using Web-Crawled Videos
Seunghoon Hong, Donghun Yeo, Suha Kwak, Honglak Lee, Bohyung Han
In CVPR 2017 , Spotlight presentation
[arXiv preprint]


 

Decomposing Motion and Content for Natural Video Sequence Prediction
Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee
In ICLR 2017
[pdf] [Project page ]


 

Personalized Image Aesthetic Quality Assessment by Joint Regression and Ranking
Kayoung Park, Seunghoon Hong, Mooyeol Baek, Bohyung Han
In WACV 2017
[pdf]


 

Weakly Supervised Semantic Segmentation using Superpixel Pooling Network
Suha Kwak, Seunghoon Hong, Bohyung Han
In AAAI 2017
[pdf]


 

Learning Transferrable Knowledge for Semantic Segmentation
with Deep Convolutional Neural Network

Seunghoon Hong, Junhyuk Oh, Bohyung Han, Honglak Lee
In CVPR 2016, Spotlight presentation (Acceptance = 123/1865~9%)
[arXiv preprint][Project page]


 

Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
*Seunghoon Hong, *Hyeonwoo Noh, Bohyung Han
In NIPS 2015, Spotlight presentation (Acceptance = 82/1838~4.5%)
(* both authors have equal contribution)
[arXiv preprint][Project page]


 

Learning Deconvolution Network for Semantic Segmentation
Hyeonwoo Noh, Seunghoon Hong, Bohyung Han
In ICCV 2015
[arXiv preprint][Project page]


 

Joint Image Clustering and Labeling by Matrix Factorization
Seunghoon Hong, Jonghyun Choi, Jan Feyereisl, Bohyung Han, Larry S. Davis
In TPAMI
[pdf]


 

Online Tracking by Learning Discriminative Saliency Map with
Convolutional Neural Network

Seunghoon Hong, Tackgeun You, Suha Kwak, Bohyung Han
In ICML 2015 (Acceptance = 270/1037~26%)
[arXiv preprint]


 

Visual Tracking by Sampling Tree-Structured Graphical Models
Seunghoon Hong, Bohyung Han
In ECCV 2014, Oral presentation (Acceptance = 38/1444~2.6%)
[pdf] [Project page]


 

Online Graph-Based Tracking
Hyeonseob Nam, Seunghoon Hong, Bohyung Han
In ECCV 2014
[pdf] [Project page]


 

Orderless Tracking through Model-Averaged Posterior Estimation
Seunghoon Hong, Suha Kwak, Bohyung Han
In ICCV 2013, Oral presentation (Acceptance = 41/1633~2.5%)
[pdf] [Project page]


 

Joint Segmentation and Pose Tracking of Human in Natural Videos
Taegyu Lim, Seunghoon Hong, Bohyung Han, Joon Hee Han
In ICCV 2013
[pdf] [Dataset]

Awards and Honors

Invited Talks

Education

Research Experience

Projects

Flag Counter