Suha Kwak

  Associate Professor
  Computer Vision Lab
  Graduate School of AI / Dept. of CSE
  POSTECH
  Pohang, Korea

I am an associate professor in Artificial Intelligence and Computer Science and Engineering at POSTECH, and a faculty member of POSTECH Computer Vision Lab. Before that, I spent one and half years on the faculty of the Department of Information and Communication Engineering at DGIST. I did a post-doc with Ivan Laptev and Jean Ponce in the WILLOW team at the Department of Computer Science of the École Normale Supérieure and Inria Paris. 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.

I am primarily interested in label efficient learning, metric learning, domain adaptation and generalization, multimodal learning, and robustness of visual recognition. My research interests also include video understanding and medical image analysis.


News

11 / 2021
Sungyeon won the best paper runner up award at the Electronic Times ICT Paper Contest.
10 / 2021
Three papers are accepted to appear at BMVC 2021.
10 / 2021
A paper on medical image synthesis is accepted for publication in Scientific Reports.
10 / 2021
A paper on video understanding is accepted to appear at NeurIPS 2021.
08 / 2021
Two papers on person search and video understanding are accepted to appear at ICCV 2021.
06 / 2021
I will be serving as an Area Chair of CVPR 2022.
05 / 2021
A paper on knowledge transfer for deep metric learning is accepted to appear at CVPR 2021.
05 / 2021
A paper on modeling penultimate activations of classification networks is accepted to appear at UAI 2021.
02 / 2021
Sungyeon, Dongwon, Boseung, and Jicheol won grand and bronze prizes at IPIU 2021.
01 / 2021
Sungyeon and Tackgeun won Naver Ph.D Fellowship.
01 / 2021
Sungyeon won the Qualcomm Innovation Fellowship for his work "Deep Metric Learning Beyond Binary Supervision".
12 / 2020
I will be serving as an Area Chair of ICCV 2021 and MVA 2021.
12 / 2020
A paper on medical image synthesis is accepted to appear at WACV 2021.
07 / 2020
Two papers on robust visual recognition and video action recognition are accepted to appear at ECCV 2020.
03 / 2020
A paper on deep metric learning is accepted to appear at CVPR 2020.
03 / 2020
I have joined the editorial board of IJCV as an associate editor.

Selected Publications

Relational Self-Attention: What's Missing in Attention for Video Understanding
Manjin Kim*, Heeseung Kwon*, Chunyu Wang, Suha Kwak, and Minsu Cho
(*equal contribution)
Annual Conference on Neural Information Processing Systems (NeurIPS), 2021
ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer
Boseung Jeong*, Jicheol Park*, and Suha Kwak (*equal contribution)
IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
Heeseung Kwon*, Manjin Kim*, Suha Kwak, and Minsu Cho
(*equal contribution)
IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Embedding Transfer with Label Relaxation for Improved Metric Learning
Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
URIE: Universal Image Enhancement for Visual Recognition in the Wild
Taeyoung Son, Juwon Kang, Namyup Kim, Sunghyun Cho, and Suha Kwak
European Conference on Computer Vision (ECCV), 2020
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
Heeseung Kwon, Manjin Kim, Suha Kwak, and Minsu Cho
European Conference on Computer Vision (ECCV), 2020
Proxy Anchor Loss for Deep Metric Learning
Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Deep Metric Learning Beyond Binary Supervision Oral
Sungyeon Kim, Minkyo Seo, Ivan Laptev, Minsu Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations Oral
Jiwoon Ahn, Sunghyun Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Domain Specific Batch Normalization for Unsupervised Domain Adaptation
Woong-Gi Chang*, Tackgeun You*, Seonguk Seo*, Suha Kwak, and Bohyung Han
(*equal contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
Jiwoon Ahn and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Weakly Supervised Semantic Segmentation Using Web-Crawled Videos Spotlight
Seunghoon Hong, Donghun Yeo, Suha Kwak, Honglak Lee, and Bohyung Han
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation
Suha Kwak, Minsu Cho, and Ivan Laptev
IEEE/CVF 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
IEEE/CVF International Conference on Computer Vision (ICCV), 2015
Unsupervised Object Discovery and Localization in the Wild Oral
Minsu Cho, Suha Kwak, Cordelia Schmid, and Jean Ponce
IEEE/CVF 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
Object Localization based on Structural SVM using Privileged Information
Jan Feyereisl, Suha Kwak, Jeany Son, and Bohyung Han
Annual Conference on Neural Information Processing Systems (NeurIPS), 2014
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), 2014
Orderless Tracking through Model-Averaged Posterior Estimation Oral
Seunghoon Hong, Suha Kwak, and Bohyung Han
IEEE/CVF International Conference on Computer Vision (ICCV), 2013
Multi-Agent Event Detection: Localization and Role Assignment
Suha Kwak, Bohyung Han, and Joon Hee Han
IEEE/CVF 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
IEEE/CVF International Conference on Computer Vision (ICCV), 2011
Learning Occlusion with Likelihoods for Visual Tracking
Suha Kwak, Woonhyun Nam, Bohyung Han, and Joon Hee Han
IEEE/CVF International Conference on Computer Vision (ICCV), 2011

Our Team

 PhD Students

  • Tackgeun You (co-advised with Prof. Bohyung Han)
  • Dongkeun Kim
  • Minkyo Seo
  • Namyup Kim
  • Jicheol Park
  • Juwon Kang
  • Sungyeon Kim
  • Sehyun Hwang
  • Boseung Jeong
  • Dongwon Kim
  • Nayeong Kim
  • Youngseok Yoon
  • Taeyoung Son
  • Sohyun Lee
  • Donghyun Kwon
  • Hyunjoon Lee

 MS Students

  • Jinsung Lee

 Undergraduate Students

  • Junhyeong Cho
  • Inho Kim
  • Taegyu Park

 Alumni

  • Kyungmoon Lee (MS 2021)
  • Daniel Kim (MS 2020, co-advised with Prof. Bohyung Han)
  • Sunwoo Oh (MS 2020, co-advised with Prof. Bohyung Han)
  • Jaeyong Park (MS 2019, co-advised with Prof. Sunghyun Cho)
  • Jiwoon Ahn (MS 2019, co-advised with Prof. Sunghyun Cho)
  • Woong Gi Chang (MS 2019, co-advised with Prof. Bohyung Han)
  • Wonseok Lee (MS 2019, co-advised with Prof. Bohyung Han)
  • Mooyeol Baek (MS 2018, co-advised with Prof. Bohyung Han)
  • Jicheol Park (MS 2018, co-advised with Prof. Sang Hyuk Son)

Contact

Address:
   
315 B2, POSTECH
77 Cheongam-ro, Nam-gu
Pohang, Gyungbuk
37673 Korea
Email:
   
suha dot kwak at postech dot ac dot kr
Phone:
   
+82-54-279-2390