Paper 'JT-MGCN: Joint-temporal Motion Graph Convolutional Network for Skeleton-Based Action Recognition' published at IEEE ICPR 2020
Paper 'Motion regeneration using motion texture and autoencoder' presented at SIGGRAPH Asia 2018 (Poster Session)
Paper 'On-line Color Model Learning for Adaptive Skin Segmentation' published at Korea Computer Congress 2015
Project 'Mosaicer: Automatic Pixelation of Untargeted Faces on Videos' won Grand Prize at NAVER crop
Entrance Examination Scholarship (Merit-based), Kyung Hee University (02/2018–08/2019)
Excellence Award (Graduated with the highest honor in class), Kyung Hee University (02/2018)
National Science Technology Scholarship, Korea Student Aid Foundation (03/2016–08/2017)
Superiority Scholarship (Merit-based), Kyung Hee University (08/2014–02/2015)
Research Experience
Multi-view Multi-persons 3D Pose Estimation: Predicting human poses using multiview images
3D Personal Avatar Generation for Augmented Reality: Real-time pose prediction using voxel datasets from multi-view depth cameras; inferring 3D body shapes and textures from 2D multi-view images
Action Recognition Methods Effective for Both Spatial and Temporal Features: Evolved from manual feature extraction to CNN/LSTM-based approaches, and finally to adaptive graph structures modeling spatio-temporal correlations
Evaluation of Gesture Recognition Algorithms for Embedded Devices: Benchmarking a custom CNN algorithm against traditional computer vision and other CNN methods on real embedded AI hardware
Automatic Color Correction on 2D Product Images for Ecommerce: Aligning color between lifestyle and plain product images via correspondence and transformation networks
Real-time Color Model Learning for Adaptive Skin Segmentation: Segmenting personal skin in videos using an adaptive Gaussian color model