Suha Kwak

  Assistant Professor
  Department of Information and Communication Engineering
  DGIST (Daegu Gyeongbuk Institute of Science and Technology)

I am an assistant professor in Information and Communication Engineering at DGIST. Before joining DGIST, I was a postdoctoral researcher at Inria, and working with Ivan Laptev and Jean Ponce in the WILLOW team at the Department of Computer Science of the École Normale Supérieure. I completed my BS and PhD in 2007 and 2014, respectively, both at POSTECH, where I was advised by Prof. Joon Hee Han and Prof. Bohyung Han in the Computer Vision Lab. My research is in computer vision and machine learning. I'm primarily interested in problems related to video understanding such as object detection, tracking, and human behavior analysis. My research interests also include topics in machine learning such as deep learning, structured prediction, and weakly supervised learning.


News

08 / 2017
A survey paper on weakly supervised semantic segmentation is accepted in IEEE Signal Processing Magazine.
03 / 2017
A paper on weakly supervised semantic segmentation using web-crawled videos is accepted to CVPR 2017.
11 / 2016
A paper on weakly supervised semantic segmentation is accepted to AAAI 2017.
07 / 2016
I'm going to join DGIST as an assistant professor in this fall.
04 / 2016
A paper on deep pose embedding is accepted to CVPR 2016.

Selected Publications

Weakly Supervised Semantic Segmentation Using Web-Crawled Videos
Seunghoon Hong, Donghun Yeo, Suha Kwak, Honglak Lee, and Bohyung Han
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network
Suha Kwak, Seunghoon Hong, and Bohyung Han
AAAI Conference on Artificial Intelligence (AAAI), 2017.
Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation
Suha Kwak, Minsu Cho, and Ivan Laptev
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
Unsupervised Object Discovery and Tracking in Video Collections
Suha Kwak, Minsu Cho, Ivan Laptev, Jean Ponce, and Cordelia Schmid
International Conference on Computer Vision (ICCV), 2015.
Unsupervised Object Discovery and Localization in the Wild
Minsu Cho, Suha Kwak, Cordelia Schmid, and Jean Ponce
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
Seunghoon Hong, Tackgeun You, Suha Kwak, and Bohyung Han
International Conference on Machine Learning (ICML), 2015.
Online Video Event Detection by Constraint Flow
Suha Kwak, Bohyung Han, and Joon Hee Han
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 26(6), 1174-1186, 2014.
Orderless Tracking through Model-Averaged Posterior Estimation
Seunghoon Hong, Suha Kwak, and Bohyung Han
International Conference on Computer Vision (ICCV), 2013.
Multi-Agent Event Detection: Localization and Role Assignment
Suha Kwak, Bohyung Han, and Joon Hee Han
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
Generalized Background Subtraction Based on Hybrid Inference by Belief Propagation and Bayesian Filtering
Suha Kwak, Taegyu Lim, Woonhyun Nam, Bohyung Han, and Joon Hee Han
International Conference on Computer Vision (ICCV), 2011.
Learning Occlusion with Likelihoods for Visual Tracking
Suha Kwak, Woonhyun Nam, Bohyung Han, and Joon Hee Han
International Conference on Computer Vision (ICCV), 2011.

Contact

Address

   
Room 313, Bld. E3, DGIST
333 Techno Jungang Daero
Hyeonpung-Myeon, Dalseong-Gun
Deagu, 42988 Korea

Email

   
skwak at dgist dot ac dot kr

Phone

   
+82-53-785-6321