Research
Research Interests
Transfer learning (Domain adaptation and generalization)
Deep neural network architecture for visual recognition
Medical imaging, face recognition, and visual tracking
Transfer learning (Feature learning and Domain adaptation / generalization)
(Selected papers in the recent 3-years)
Unsupervised feature learning for self-tuning neural networks.
Jongbin Ryu, Ming-Hsuan Yang, and Jongwoo Lim.
Neural Networks, 2021.
Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition
Jongbin Ryu, GiTaek Kwon, Ming-Hsuan Yang, and Jongwoo Lim.
International Conference on Learning Representations (ICLR), 2020.
Unsupervised Face Domain Transfer for Low-Resolution Face Recognition
Sungeun Hong and Jongbin Ryu* (corresponding author)
IEEE Signal Processing Letters (SPL), 2020
Deep neural network architecture
(Selected papers in the recent 3-years)
Dual Aggregated Feature Pyramid Network for Multi Label Classification
Dongjoo Yun, Jongbin Ryu*, Jongwoo Lim (corresponding author),
Pattern Recognition Letters, 2021
DFT-based Transformation Invariant Pooling Layer for Visual Classification.
Jongbin Ryu, Ming-Hsuan Yang, and Jongwoo Lim
European Conference on Computer Vision (ECCV), 2018.
Others (Medical imaging, Depth estimation, and video segmentation)
(Selected papers in the recent 3-years)
Deep learning algorithms for detecting and visualising intussusception on plain abdominal radiography in children: a retrospective multicenter study.
Gitaek Kwon*, Jongbin Ryu*, Jaehoon Oh, Jongwoo Lim, Bo-kyeong Kang, Chiwon Ahn, Junwon Bae, and Dong Keon Lee. (* equal contribution)
Scientific reports 2020.
OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching
Changhee Won, Jongbin Ryu, and Jongwoo Lim
IEEE International Conference on Computer Vision (ICCV), 2019
SweepNet: Wide-baseline Omnidirectional Depth Estimation
Changhee Won, Jongbin Ryu, and Jongwoo Lim
IEEE International Conference on Robotics and Automation (ICRA), 2019
Joint Object Tracking and Segmentation with Independent Convolutional Neural Networks
Hakjin Lee, Jongbin Ryu, and Jongwoo Lim
Coview: 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild, in conjuction with ACM MM, 2018