249 citations
- Seoul National UniversityKR12 papers
- Korea Institute for Advanced StudyKR9 papers
- Sungkyunkwan UniversityKR7 papers
- Korea Advanced Institute of Science and TechnologyKR6 papers
- Institute for Basic ScienceKR5 papers
- Hankuk University of Foreign StudiesKR4 papers
- Novo Nordisk (Denmark)DK4 papers
- Pohang University of Science and TechnologyKR4 papers
- Umeå UniversitySE4 papers
- Yonsei UniversityKR4 papers
- Hanyang UniversityKR3 papers
- Korea Institute of Science & Technology InformationKR3 papers
9 papers · 1 filter
Continuous Facial Motion Deblurring
Tae Bok Lee, Sujy Han, Yong Seok Heo
We introduce a novel framework for continuous facial motion deblurring that restores the continuous sharp moment latent in a single motion-blurred face image via a moment control f…
A Facial Feature Discovery Framework for Race Classification Using Deep Learning
Khalil Khan, Jehad Ali, Irfan Uddin +2
Race classification is a long-standing challenge in the field of face image analysis. The investigation of salient facial features is an important task to avoid processing all face…
FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
Jaemin Na, Heechul Jung, Hyung Jin Chang +1
Unsupervised domain adaptation (UDA) methods for learning domain invariant representations have achieved remarkable progress. However, most of the studies were based on direct adap…
Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
Sijin Kim, Namhyuk Ahn, Kyung-Ah Sohn
In recent years, deep learning-based methods have been successfully applied to the image distortion restoration tasks. However, scenarios that assume a single distortion only may n…
SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-resolution
Namhyuk Ahn, Jaejun Yoo, Kyung-Ah Sohn
In this paper, we tackle a fully unsupervised super-resolution problem, i.e., neither paired images nor ground truth HR images. We assume that low resolution (LR) images are relati…
Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Network
Junho Jo, Hyung Il Koo, Jae Woong Soh +1
We present a new handwritten text segmentation method by training a convolutional neural network (CNN) in an end-to-end manner. Many conventional methods addressed this problem by…