Soonmin Hwang

Yonsei University — South Korea

Computer Science · Physical Sciences

10h-index1.8kcitations35works1.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(10), Video Surveillance and Tracking Methods(9), Robotics and Sensor-Based Localization(7), Advanced Vision and Imaging(6), Autonomous Vehicle Technology and Safety(6)

Publications35 total

End-to-end Radio SLAM for Autonomous Systems
2025
RoCaRS: Robust Camera-Radar BEV Segmentation for Sensor Failure Scenarios
2025
Boosting Cross-Spectral Unsupervised Domain Adaptation for Thermal Semantic Segmentation
2025
Boosting Cross-spectral Unsupervised Domain Adaptation for Thermal Semantic Segmentation
arXiv (Cornell University)·2025Open Access
DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 5 citedOpen Access
Efficient Occupancy Prediction with Instance-Level Attention
2025
Leveraging Camera-Based Methods for Enhanced Feature-to-World Mapping
2025
DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation
arXiv (Cornell University)·2024Open Access
SafeShift: Safety-Informed Distribution Shifts for Robust Trajectory Prediction in Autonomous Driving
2024· 9 cited
UMHE: Unsupervised Multispectral Homography Estimation
IEEE Sensors Journal·2024· 2 cited
Empirical Study: Monocular Depth Estimation from RGB, NIR, Thermal Image in Adverse Weather Conditions
2023
T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Prediction
2023· 2 cited
SafeShift: Safety-Informed Distribution Shifts for Robust Trajectory Prediction in Autonomous Driving
arXiv (Cornell University)·2023Open Access
Instant Domain Augmentation for LiDAR Semantic Segmentation
2023· 17 cited
Instant Domain Augmentation for LiDAR Semantic Segmentation
arXiv (Cornell University)·2023· 1 citedOpen Access
T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Prediction
arXiv (Cornell University)·2022Open Access
TransDSSL: Transformer Based Depth Estimation via Self-Supervised Learning
IEEE Robotics and Automation Letters·2022· 36 cited
Gated bidirectional feature pyramid network for accurate one-shot detection
Machine Vision and Applications·2019· 26 citedOpen Access
Learning based adaptive visual sensor fusion for robust pedestrian detection = 강인한 보행자 검출을 위한 학습 기반 적응적 시각 센서 융합 기법
2019
Multispectral Transfer Network: Unsupervised Depth Estimation for All-Day Vision
Proceedings of the AAAI Conference on Artificial Intelligence·2018· 49 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Yukyung Choi(15), In So Kweon(13), Nam Il Kim(7), Namil Kim(7), Jean Oh(5), Kibaek Park(4), Jae Shin Yoon(4), Jeongmin Shin(4), Benjamin Stoler(4), Meghdeep Jana(4), Jaesik Park(3), S. M. Kwon(3), Sanghyun Woo(2), Kwonyoung Ryu(2), Ingrid Navarro(2), Jonathan Francis(2), Jisoo Kim(2), Jungbin Cho(2), Joonho Park(2), Da Eun Kim(2)