Yumin Suh

Yumin Suh

E-mail: yumin (at) nec-labs.com
CV
Google Scholar
Github

About Me

I am a researcher at NEC Labs America. I received my PhD at Seoul National University in 2019, advised by Kyoung Mu Lee. Before joining NEC, I worked as a postdoctoral researcher at Seoul National University, advised by Bohyung Han and Kyoung Mu Lee. My research interests are in computer vision and machine learning.

Publications

Cross-Domain Similarity Learning for Face Recognition in Unseen Domains

Masoud Faraki, Xiang Yu, Yi-Hsuan Tsai, Yumin Suh, Manmohan Chandraker
CVPR 2021 [Paper]

Learning to Optimize Domain Specific Normalization for Domain Generalization

Seonguk Seo, Yumin Suh, Dongwan Kim, Geeho Kim, Jong-Woo Han, and Bohyung Han
ECCV 2020 [Paper]

Stochastic Class-based Hard Example Mining for Deep Metric Learning

Yumin Suh, Bohyung Han, Wonsik Kim, and Kyoung Mu Lee
CVPR 2019 [Paper]

Part-Aligned Bilinear Representations for Person Re-identification

Yumin Suh, Jingdong Wang, Siyu Tang, Tao Mei and Kyoung Mu Lee
ECCV 2018 [Paper] [Supp] [Code] [Poster]

Appearance Dependent Inter-Part Relationship for Human Pose Estimation

Yumin Suh and Kyoung Mu Lee
APSIPA 2016

Discrete Tabu Search for Graph Matching

Kamil Adamczewski, Yumin Suh, and Kyoung Mu Lee
ICCV 2015 [Paper]

Subgraph Matching using Compactness Prior for Robust Feature Correspondence

Yumin Suh, Kamil Adamczewski, and Kyoung Mu Lee
CVPR 2015 [Paper]

Graph Matching via Sequential Monte Carlo

Yumin Suh, Minsu Cho, and Kyoung Mu Lee
ECCV 2012 [Paper]

Roles of Time Hazard in Perceptual Decision Making under High Time Pressure

Minju Kim, Yumin Suh, Daeseob Lim, Issac Rhim, Kyoung-Whan Choi, and Sang- Hun Lee
i-Perception 2(4), 2011

Tech Reports

Cross-Modal Prediction Consistency based Self-Training for Unsupervised Domain Adaptation

Dongwan Kim, Geeho Kim, Seonguk Seo, Yumin Suh, Bohyung Han, Taeho Lee, Jongwoo Han, and Hyejeong Jeon
3rd Place in VisDA-2019 Challenge [Paper]

Domainwise Batch Normalization for Unsupervised Domain Adaptation

Seonguk Seo*, Yumin Suh*, Woong-Gi Chang, Tackgeun You, Suha Kwak, Taeho Lee, and Bohyung Han
ICML 2019 Workshop on Understanding and Improving Generalization in Deep Learning [Paper]

Holistic planimetric prediction to local volumetric prediction for 3d human pose estimation

Gyeongsik Moon, Ju Yong Chang, Yumin Suh, Kyoung Mu Lee
arXiv 2017 [Paper]

Experience

Researcher at NEC Labs America. 2019.12 - present

Postdoctoral researcher at Seoul National University, Seoul, Korea. 2019.4 - 2019.11
Advisors: Bohyung Han, Kyoung Mu Lee

Research Intern at Microsoft Research Asia (MSRA), Beijing, China. 2016.9 - 2017.5
Advisors: Tao Mei, Jingdong Wang

Research Intern at WILLOW, Inria, Paris, France. 2014.12 - 2015.6
Advisors: Jean Ponce, Minsu Cho

Academic Services

Reviewer

ACCV 2020, CVPR 2019-2021, ECCV 2020, ICCV 2019-2021, ICPR 2020, MM 2017, WACV 2021
AAAI 2020-2021, ICLR 2021-2022, ICML 2020-2021, NeurIPS 2021
TPAMI, TIP, TMM, CVIU, MMSJ, AOAS, TCSVT

Senior Program Committee

IJICAI 2021, AAAI 2022

Outstanding Reviewer

ICML 2020

Student Volunteer

ACCV 2012, MM 2018