Embedded Files
Ph. D. Candidate
Image and Video Systems Laboratory
Korea Advanced Institute of Science and Technology (KAIST)
School of Electrical Engineering
email: greatday [at] kaist.ac.kr
Research Interests:
Robust AI, Causal AI, Large-scale Vision-Language Model
Education
KAIST, Daejeon, Korea (2020-Present)
Ph.D. in Electrical Engineering
Advisor: Prof. Yong Man Ro
KAIST, Seoul, Korea (2014-2017)
M.S. in Management Engineering
KAIST, Daejeon, Korea (2014)
B.S. in Electrical Engineering
Publications
Advancing Causal Intervention in Image Captioning with Causal Prompt
Youngjoon Yu, Yeonju Kim, and Yong Man Ro
IEEE Transactions on Neural Network and Learning Systems (TNNLS), 2024 [JCR Top 6.3%, Impact Factor: 10.2]
Revisiting Misalignment in Multispectral Pedestrian Detection: A Language-driven Approach for Cross-modal Alignment Fusion
Taeheon Kim*, Sangyun Chung*, Youngjoon Yu*, and Yong Man Ro (* equal contribution)
IEEE International Conference on Image Processing (ICIP), 2024
Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection
Taeheon Kim*, Sebin Shin*, Youngjoon Yu, Hak Gu Kim, Yong Man Ro (* equal contribution)
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2024
Multispectral Invisible Coating: Laminated Visible-Thermal Physical Attack against Multispectral Object Detectors using Transparent Low-e films
Taeheon Kim, Youngjoon Yu, and Yong Man Ro
Conference on Association for the Advancement of Artificial Intelligence (AAAI), 2023
Advancing Adversarial Training by Injecting Booster Signal
Hong Joo Lee, Youngjoon Yu, and Yong Man Ro
IEEE Transactions on Neural Network and Learning Systems (TNNLS), 2023 [JCR Top 6.3%, Impact Factor: 10.2]
Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Frame
Youngjoon Yu*, Hong Joo Lee*, Hakmin Lee and Yong Man Ro (* equal contribution)
IEEE Transactions on Image Processing (TIP), 2022 [JCR Top 3.8%, Impact Factor: 10.8]
Defending Physical Adversarial Attack on Object Detection via Adversarial Patch-Feature Energy
Taeheon Kim, Youngjoon Yu, Yong Man Ro
ACM International Conference on Multimedia (ACM MM), 2022
Robust Decision-based Black-box Adversarial Attack via Coarse-to-fine Random Search
Byeong Cheon Kim*, Youngjoon Yu*, and Yong Man Ro (* equal contribution)
IEEE International Conference on Image Processing (ICIP), 2021
Towards Robust Training of Multi-sensor Data Fusion Network Against Adversarial Examples in Semantic Segmentation
Youngjoon Yu, Hong Joo Lee, Byeong Cheon Kim, Jung Uk Kim, and Yong Man Ro
IEEE/CVF International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
Investigating Vulnerability to Adversarial Examples on Multimodal Data Fusion in Deep Learning
Youngjoon Yu, Hong Joo Lee, Byeong Cheon Kim, Jung Uk Kim, and Yong Man Ro
arXiv preprint arXiv:2005.10987, 2020
Professional Activities
Reviewer of IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Reviewer of IEEE Transactions on Neural Network and Learning Systems (TNNLS)
Reviewer of IEEE Transactions on Image Processing (TIP)
Reviewer of IEEE/CVF Computer Vision and Pattern Recognition (CVPR)
Reviewer of IEEE/CVF International Conference on Computer Vision (ICCV)
Reviewer of Conference on Association for the Advancement of Artificial Intelligence (AAAI)
Reviewer of European Conference on Computer Vision (ECCV)
Reviewer of IEEE/CVF International Conference of Acoustics, Speech, and Signal Processing (ICASSP)
Awards & Honors
The Best Presentation Award
KAIST-Korea Agency for Defence Development Workshop, 2022
The Best Paper Award
Military Operations Research Society of Korea, 2020
News Articles
- 딥러닝, 적대적 공격 막는 방어 프레임 개발...KAIST, 인공지능 방어 성능 강화!, AI Times, 2022.11.15
Page updated
Report abuse