Scholar
Hyeonggon Ryu
Google Scholar ID: v9BcFogAAAAJ
KAIST
Citations & Impact
Citations
200
H-index
6
i10-index
5
Publications
12
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- - 2025: CVPR, Seeing Speech and Sound: Distinguishing and Locating Audio Sources in Visual Scenes
- - 2024: ICASSP, Speech Guided Masked Image Modeling for Visually Grounded Speech
- - 2023: ICASSP, Hindi as a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples; CVPR, Generative Bias for Robust Visual Question Answering; ICCV, Sound Source Localization is all about Cross-Modal Alignment
- - 2022: WACV, Less Can Be More: Sound Source Localization With a Classification Model, Honorable Mention, 28th HumanTech Paper Award, Samsung Electronics Co., Ltd; ICASSP, Learning Sound Localization Better from Semantically Similar Samples; arXiv preprint, Audio-Visual Fusion Layers for Event Type Aware Video Recognition
Research Experience
- - Internship in MARG Lab., SNU, South Korea, Jul. 2020 - Aug. 2020, Advisor: Kyogu Lee, Research: Text-to-speech, Sound source separation
- - Exchange student, Uppsala University, Sweden, Sep. 2019 - Jan. 2020
- - Internship in RCV Lab., KAIST, South Korea, Jul. 2019 - Aug. 2019, Advisor: In So Kweon, Research: Image captioning
- - Military Service, Seoul Air Base, South Korea, Sep. 2016 - Sep. 2018, Served as an assistant maintenance technician
Education
- - Ph.D. in KAIST, South Korea, Mar. 2023 - Present, Advisor: Professor Joon Son Chung
- - M.S. in KAIST, South Korea, Mar. 2021 - Feb. 2023, Advisor: Professor In So Kweon
- - B.S. in Hanyang University, South Korea, Mar. 2015 - Feb. 2021, Graduation work: The multi-speaker deep convolutional text-to-speech model
Background
- Research Interests: Machine Learning, Computer Vision, with a focus on multi-modal machine learning (audio-visual, vision-language) and spoken language. PhD student at KAIST, advised by Professor Joon Son Chung.
Miscellany
- Personal interests not provided
