J
Jangho Lee
Researcher at Seoul National University
Publications - 21
Citations - 789
Jangho Lee is an academic researcher from Seoul National University. The author has contributed to research in topics: Frame (networking) & Computer science. The author has an hindex of 9, co-authored 18 publications receiving 491 citations.
Papers
More filters
Proceedings ArticleDOI
FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference
TL;DR: FickleNet explores diverse combinations of locations on feature maps created by generic deep neural networks and implicitly learns the coherence of each location in the feature maps, resulting in a localization map which identifies both discriminative and other parts of objects.
Posted Content
FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference.
TL;DR: FickleNet as discussed by the authors explores diverse combinations of locations on feature maps created by generic deep neural networks and then uses them to obtain activation scores for image classification for weakly supervised semantic image segmentation.
Posted Content
LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems.
TL;DR: A novel ensemble method that blends multiple thresholding classifiers into a single one, making it possible to accumulate 'highly normal' sequences to remedy the issue of high false-alarm rates commonly arising in conventional methods.
Journal ArticleDOI
Single-image deblurring with neural networks: A comparative survey
TL;DR: It is found that multi-scale training helps NNs to deal with large blurs, and RNNs outperform CNNs and GANs using a perceptual loss function produce artifacts.
Journal ArticleDOI
Large-scale machine learning of media outlets for understanding public reactions to nation-wide viral infection outbreaks.
Sung-Woon Choi,Sung-Woon Choi,Jangho Lee,Min Gyu Kang,Hyeyoung Min,Yoon-Seok Chang,Sungroh Yoon,Sungroh Yoon +7 more
TL;DR: A plausible explanation for the public overreaction to MERS is discovered in terms of the interplay between the disease, mass media, and public emotions in terms that included techniques for extracting emotions from emoticons and Internet slang.