Research Interests

Multimodal Learning

Self-supervised Learning

Social Artificial Intelligence

Experience

Georgia Institute of Technology (Georgia Tech), GA, United States (Oct 2023 - Present) 

University of Illinois Urbana-Champaign (UIUC), IL, United States (May 2023 - Present) 

Education

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea (Feb 2017 - Feb 2023) 

Yonsei University, Seoul, South Korea (Mar 2012 - Feb 2017) 

Publications

1. Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations

2. Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge

3. Audio-Visual Mismatch-Aware Video Retrieval via Association and Adjustment

4. Weakly Paired Associative Learning for Sound and Image Representations via Bimodal Associative Memory

5. Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning

6. CUA Loss: Class Uncertainty-Aware Gradient Modulation for Robust Object Detection

7. Assessing Individual VR Sickness through Deep Feature Fusion of VR Video and Physiological Response

8. Towards a Better Understanding of VR Sickness: Physical Symptom Prediction for VR Contents

9. Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images

10. SACA Net: Cybersickness Assessment of Individual Viewers for VR Content via Graph-based Symptom Relation Embedding

11. Structure Boundary Preserving Segmentation for Medical Image With Ambiguous Boundary

12. Video Frame Interpolation via Exceptional Motion-aware Synthesis

13. BMAN: Bidirectional Multi-scale Aggregation Networks for Abnormal Event Detection

14. Robust Video Frame Interpolation with Exceptional Motion Map

15. Estimating VR Sickness Caused by Camera Shake in VR Videography

16. Physiological Fusion Net: Quantifying Individual VR Sickness with Content Stimulus and Physiological Response

17. Deep Objective Assessment Model Based on Spatio-temporal Perception of 360-Degree Video for VR Sickness Prediction

18. VRSA Net: VR Sickness Assessment considering Exceptional Motion for 360-degree VR Video

19. On-the-Fly Facial Expression Prediction using LSTM Encoded Appearance-Suppressed Dynamics

20. STAN: Spatio-temporal Adversarial Networks for Abnormal Event Detection

Patents

1. Method for Video Frame Interpolation Robust to Exceptional Motion and the Apparatus Thereof

Korea Patent 2244187 / PCT Patent App. 003461 

2. Method for VR Sickness Assessment Considering Neural Mismatch Model and the Apparatus Thereof

Korea Patent 2284266 / US Patent 11699072 

3. Apparatus and Method for Virtual Reality Sickness Reduction Based on Virtual Reality Sickness Assessment

Korea Patent 2291257 / US Patent 11252371  

4. Video Sequences Generating System Using Generative Adversarial Networks and the Method Thereof

Awards & Honors

1st Place Winner of Ad-hoc Video Search Competition (2022)

Samsung HumanTech Paper Award, Honor Prize ($2,000) (2021)

Outstanding Project Selection (Graduate Project Lead) (2020)

Outstanding TA Award (2 Times) (2019, 2020)

ICIP Best Paper Finalist (2019)

ICIP Top 10% Paper Selection (2019)

National Government Fellowship (2017 - 2023)

Professional Activities

Reviewer

Invited Talks

Teaching