D
Dongwoo Kim
Researcher at Pohang University of Science and Technology
Publications - 62
Citations - 570
Dongwoo Kim is an academic researcher from Pohang University of Science and Technology. The author has contributed to research in topics: Computer science & Topic model. The author has an hindex of 11, co-authored 44 publications receiving 385 citations. Previous affiliations of Dongwoo Kim include KAIST & Australian National University.
Papers
More filters
Proceedings ArticleDOI
Invertible Denoising Network: A Light Solution for Real Noise Removal
TL;DR: InvDN as mentioned in this paper replaces the noisy latent representation with another one sampled from a prior distribution during reversion to discard noise and restore the clean image, achieving a new state-of-the-art result for the SIDD dataset.
Proceedings Article
Context-dependent conceptualization
Dongwoo Kim,Haixun Wang,Alice Oh +2 more
TL;DR: A corpus-based framework for context-dependent conceptualization is developed which improves conceptualization and enable a wide range of applications that rely on semantic understanding of short texts, including frame element prediction, word similarity in context, ad-query similarity, and query similarity.
Book ChapterDOI
Topic chains for understanding a news corpus
Dongwoo Kim,Alice Oh +1 more
TL;DR: This work presents a framework, based on probabilistic topic modeling, for uncovering the meaningful structure and trends of important topics and issues hidden within the news archives on the Web.
Proceedings ArticleDOI
Modeling topic hierarchies with the recursive chinese restaurant process
TL;DR: This work introduces the recursive Chinese restaurant process (rCRP) and a nonparametric topic model with rCRP as a prior for discovering a hierarchical topic structure with unbounded depth and width and suggests two metrics that quantify the characteristics of a topic hierarchy to compare the discovered topic hierarchies of r CRP and nCRP.
Posted Content
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator.
Zhenyue Qin,Dongwoo Kim +1 more
TL;DR: In this article, the authors propose an informative class activation map, which highlights regions of the input image that are the most relevant to a given label based on differences in information, which helps localize the target object in an input image.