H
Hoang-Quoc Nguyen-Son
Researcher at National Institute of Informatics
Publications - 38
Citations - 198
Hoang-Quoc Nguyen-Son is an academic researcher from National Institute of Informatics. The author has contributed to research in topics: Homograph & Computer science. The author has an hindex of 7, co-authored 36 publications receiving 129 citations. Previous affiliations of Hoang-Quoc Nguyen-Son include Ho Chi Minh City University of Science & Graduate University for Advanced Studies.
Papers
More filters
Proceedings ArticleDOI
Modular Convolutional Neural Network for Discriminating between Computer-Generated Images and Photographic Images
Huy H. Nguyen,T. Ngoc-Dung Tieu,Hoang-Quoc Nguyen-Son,Vincent Nozick,Junichi Yamagishi,Isao Echizen +5 more
TL;DR: A modular CGI--PI discriminator with a customized VGG-19 network as the feature extractor, statistical convolutional neural networks as thefeature transformers, and a discriminator is built that outperformed a state-of-the-art method and achieved accuracy up to 100%.
Proceedings ArticleDOI
Identifying computer-generated text using statistical analysis
TL;DR: This work hypothesizes that human-crafted wording is more consistent than that of a computer, and proposes a method to identify computer-generated text on the basis of statistics that achieves better performance and works consistently in various languages.
Proceedings ArticleDOI
An approach for gait anonymization using deep learning
TL;DR: A gait anonymization method is developed that prevents unauthorized gait recognition and modifies the gait so that the person cannot be identified while maintaining the naturalness of the gace.
Journal ArticleDOI
Spatio-temporal generative adversarial network for gait anonymization
Ngoc Dung T. Tieu,Huy H. Nguyen,Hoang-Quoc Nguyen-Son,Junichi Yamagishi,Junichi Yamagishi,Junichi Yamagishi,Isao Echizen,Isao Echizen,Isao Echizen +8 more
TL;DR: Evaluation showed that the anonymized gaits generated with the proposed ST-GAN method are more natural than those generated with an existing method and that the proposed method outperforms the existing method in preventing gaits from being recognized by a gait recognition system.
Book ChapterDOI
Detecting Computer-Generated Text Using Fluency and Noise Features
TL;DR: A method for extracting and distinguishing the noises characteristically created by a person or a machine and which had the highest accuracy and the lowest equal error rate compared with one of state-of-the-art methods.