K
Ki-Sang Hong
Researcher at Pohang University of Science and Technology
Publications - 99
Citations - 2295
Ki-Sang Hong is an academic researcher from Pohang University of Science and Technology. The author has contributed to research in topics: Real image & Image segmentation. The author has an hindex of 23, co-authored 99 publications receiving 2082 citations. Previous affiliations of Ki-Sang Hong include Columbia University.
Papers
More filters
Proceedings ArticleDOI
RDFNet: RGB-D Multi-level Residual Feature Fusion for Indoor Semantic Segmentation
TL;DR: This paper presents a novel network that extends the core idea of residual learning to RGB-D semantic segmentation by including multi-modal feature fusion blocks and multi-level feature refinement blocks and achieves the state-of-the-art accuracy on two challenging RGB- D indoor datasets, NYUDv2 and SUNRGB-D.
Book ChapterDOI
Where Are the Ball and Players? Soccer Game Analysis with Color Based Tracking and Image Mosaick
TL;DR: This work addresses three main problems: 1) ground field extraction, 2) player and ball tracking and team identification and 3) absolute player positioning given an image sequence.
Book ChapterDOI
SRFeat: Single Image Super-Resolution with Feature Discrimination
TL;DR: A novel GAN-based SISR method that overcomes the limitation and produces more realistic results by attaching an additional discriminator that works in the feature domain and design a new generator that utilizes long-range skip connections so that information between distant layers can be transferred more effectively.
Journal ArticleDOI
Road detection in spaceborne SAR images using a genetic algorithm
TL;DR: The authors designed a grouping method based on a GA, which is a global optimization method and combined perceptual grouping factors with it and tried to reduce its overall computational cost by introducing a concept of region growing.
Journal ArticleDOI
Adaptive skin-color filter
TL;DR: Experimental results show that the adaptive skin color xlter method is robust to the variations of skin regions’ color compared to the conventional methods.