cv
Basics
| Name | Sangin Lee |
| Label | Postgraduate student |
| childultprogrammer@gmail.com | |
| Phone | 001+82 10-3304-2749 |
| Summary | I am a computer vision enthusiast exploring visual intelligence and multimodal AI for real-world perception systems |
Education
-
2024.03 - 2026.08 Seoul, South Korea
Master of Science (M.S)
Sejong University, Seoul, South Korea
AI Robotics
- Supervision : Yukyung Choi
-
2017.03 - 2024.02 Seoul, South Korea
Awards
- 2024.11.19
3rd Prize
Korean Ministry of Science and ICT (MSIT)
Awarded ETRI President Prize in the '1st Autonomous Driving AI Challenge' for vehicle complex state recognition.
- 2023.06
- 2017.09
Publications
-
2026.07 CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large Vision-Language Models
Sangin Lee and Yukyung Choi
International Conference on Machine Learning (ICML)
-
2026 Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection
Sangin Lee, Seokjun Kwon, Jeongmin Shin, Namil Kim and Yukyung Choi
Knowledge-Based Systems (KBS) UnderReview
-
2024.02 INSANet: INtra-INter Spectral Attention Network for Effective Feature Fusion of Multispectral Pedestrian Detection
Sangin Lee, Taejoo Kim, Jeongmin Shin, Namil Kim and Yukyung Choi
Sensors
Patents
-
2026.05 Token Pruning for Efficient Pixel Grounding Based on Visual-Text Similarity
Yukyung Choi and Sangin Lee
Patent No. Ongoing
Pending
-
2025.05 Multi-Modal Guided Multi-Source Learning for Object Detection
Yukyung Choi, Sangin Lee, Seokjun Kwon and Jeongmin Shin
Patent No. 10-2025-0064651
Pending
-
2023.08 Attention-based Illumination-aware Multispectral Pedestrian Detection
Yukyung Choi, Sangin Lee, Dogyeong Kim, Taejoo Kim, and Hyeongjun Kim
Patent No. 10-2023-0106387
Pending
Skills
| Programming | |
| C/C++ | |
| MATLAB | |
| Python | |
| Pytorch | |
| HuggingFace | |
| Git | |
| Docker |
Languages
| Korean | |
| Native speaker |
| English | |
| Fluent |
Interests
| Computer Vision | |
| Sensor Fusion | |
| Multimodal Perception | |
| Efficient VLM | |
| Large Vision-Language Model |
Projects
- 2023.01 - 2026.05
Development of 3D Sensor Fusion Technology for Improving Detection Performance of Unmanned Vehicles
FUNDED BY MINISTRY OF SCIENCE AND ICT (MSIT)
- Open-vocabulary perception
- Efficient VLM
- 2023.04 - 2025.12
Development of AI-based high resolution low power smart camera and machine vision integrated solution for defect detection in manufacturing
FUNDED BY MINISTRY OF TRADE, INDUSTRY & ENERGY (MOTIE)
- Object detection
- Lightweight backbone
- 2021.01 - 2023.12
Study on magnetic map matching based localization and vision based anomaly detection algorithm for electrical plant surveillance robots
FUNDED BY KOREA ELECTRIC POWER CORPORATION (KEPCO)
- Object detection
- Robot surveillance