I am a Deep Learning Researcher specializing in anomaly detection with Multimodal AI using advanced AI techniques.
Currently, I am pursuing my M.S. in Smart Factory Convergence at Sungkyunkwan University.
- Anomaly Detection
- Multimodal
- Deep Learning
- Computer Vision
- M.S. in Smart Factory Convergence, Sungkyunkwan University (2026 - Present)
- DepthGate: Confidence-Gated Depth Verification for Multimodal Industrial Anomaly Detection
- Authors: Soyeon Kim, Tae-Yong Kim, Jongpil Jeong
- ICCSA 2026 (Accepted)
| Date | Title & Topic | Link |
|---|---|---|
| 2026-01-11 | A multimodal industrial anomaly detection method based on mask training and teacherโstudent | Link |
| 2025-02-01 | A multi-scale information fusion framework with interaction-aware global attention for industrial vision anomaly detection and localization | Link |
| 2026-03-01 | Learning Multi-view Multi-class Anomaly Detection | Link |
| 2026-03-25 | Exploring plain ViT features for multi-class unsupervised visual anomaly detection | Link |
| 2026-03-30 | Unveiling Multi-View Anomaly Detection: Intra-view Decoupling and Inter-view Fusion | Link |
| 2026-04-30 | CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection | Link |
- Python (Deep Learning, Computer Vision, PyTorch, TensorFlow, OpenCV)
- CNN, Vision Transformer (ViT), AutoEncoder
- Anomaly Detection
- Multimodal Learning
- Git & GitHub (Version Control, Collaboration)
- ์๋ ์กฐ์ ๋ฐ์ดํฐ๋ฅผ ํ์ฉํ ์ด์ค ์ฆ๊ฐ ๊ธฐ๋ฐ ํ์ด๋ฐ์ด์
์๋ฐฉํฅ ์์ ์์ธก ๋ฐ ์๋ฎฌ๋ ์ด์
ํ๋ก๊ทธ๋จ
- ๋ฑ๋ก๋ฒํธ: 110171-0029501
๐ก Always open to new opportunities and collaborations!
- ๐ง Email: kimsoyeon744@g.skku.edu
- ๐ Location: South Korea ๐ฐ๐ท