Seonguk Seo CV Scholar Soundcloud

I am a fifth-year graduate student in Computer Vision Lab. under the supervision of Prof. Bohyung Han. My research interests lie in reliable deep learning, multi-modal learning, and 3D vision. I am also interested in ambient music production, interactive media art, and brand experience design. I was worked at Adobe Research as a research intern with Joon-Young Lee.


[May, 2022] I will work at Meta AI as a research scientist intern this summer.

[March, 2022] Our two papers about debiasing and neural volume rendering are accepted to CVPR 2022.

[March, 2022] I am participated in organizing the 4th Large-scale Video Object Segmentation Challenge (Youtube-VOS) workshop in conjunction with CVPR 2022.

[November, 2021] Our paper about information-theoretic bias reduction is accepted to AAAI 2022.

[October, 2021] Our interactive media art work <Ergo-sphere> is presented at maru art center, Seoul, 2021.

[December, 2020] Our installation media art work <Vender> is presented at art center nabi, Seoul, Dec - Jan 2021.

[July, 2020] Our two papers about transfer learning and video understanding are accepted to ECCV 2020.


Education

Seoul National University Mar, 2018 ~ Current Ph.D. Candidate, Computer Vision Lab.
POSTECH Mar, 2010 ~ Feb, 2018 B.S, Valedictorian and Summa Cum Laude
TU Berlin Mar, 2017 ~ Aug, 2017 Visiting Student
Seoul Science High School Mar, 2007 ~ Feb, 2010

Work Experiences

Adobe Research Research Intern Aug, 2019 ~ Oct, 2019 San Jose, CA, USA
VCNC Software Engineer Mar, 2014 ~ Feb, 2016 Seoul, Korea

Publications

2022
Unsupervised Learning of Debiased Representations with Pseudo-Attributes
Seonguk Seo, Joon-Young Lee, Bohyung Han
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, 2022
InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
Mijeong Kim, Seonguk Seo, Bohyung Han
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, 2022
Information-Theoretic Bias Reduction via Causal View of Spurious Correlation
Seonguk Seo, Joon-Young Lee, Bohyung Han
AAAI Conference on Artifical Intelligence (AAAI), Vancouver, Canada, 2022    
2020
URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark
Seonguk Seo, Joon-Young Lee, Bohyung Han
European Conference on Computer Vision (ECCV), Glasgow, UK, 2020
Learning to Optimize Domain Specific Normalization for Domain Generalization
Seonguk Seo, Yumin Suh, Dongwan Kim, Geeho Kim, Jongwoo Han, Bohyung Han
European Conference on Computer Vision (ECCV), Glasgow, UK, 2020
2019
Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
Woong-Gi Chang*, Tackgeun You*, Seonguk Seo*, Suha Kwak, Bohyung Han       (*equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019
Learning for Single-Shot Confidence Calibration in Deep Neural Networks through Stochastic Inferences
Seonguk Seo*, Paul Hongsuck Seo*, Bohyung Han       (*equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019

Awards and Honors

AAAI Student Scholarship Feb, 2022
IPIU Excellence Paper Award Feb, 2022
Youlchon AI Star Scholarship Aug, 2020
Visual Domain Adaptation Challenge (VisDA-19) Nov, 2019 ICCV 2019, 3rd Place Winner
Samsung AI Forum 2019 Best Poster Award Nov, 2019 Best Award with a Prize (from Yoshua Bengio)
Samsung AI Forum 2018 Best Poster Award Sep, 2018 Best Award with a Prize (from Yann Lecun)