Seungjin Jung's Homepage

Ph.D. Student

Department of Artificial Intelligence, Chung-Ang University

LinkedIn : [Link]

Github : [Link]

Visual Intelligence Lab. (VILab) [Homepage]

Research Interests

Machine Learning Domain Generalization Representation Learning Uncertainty Calibration

Experience

Naver CLOVA, Seongnam, Korea
Internship, Naver Clova Image Vision team., Sep.2022 - Mar. 2023.
Graduate School of Advanced Imaging Science, Multimedia & Film, Chung-Ang University, Seoul, Korea
Research Assistant, Visual Intelligence Lab., Sep. 2020 - Aug. 2022.

Education

Chung-Ang University, Seoul, Korea
Ph.D., Department of Artificial Intelligence, Sep. 2022 - Now
Adviser : Prof. Jongwon Choi
Graduate School of Advanced Imaging Science, Multimedia & Film, Chung-Ang University, Seoul, Korea
M.E., Department of Image Science and Arts, Sep. 2020 - Aug. 2022
Adviser : Prof. Jongwon Choi
Hoseo University, Asan, Korea
B.E., Department of Information and Communication Engineering, Mar. 2013 - Feb. 2020

Publications

International Paper
- Seungjin Jung*, Kanghee Lee, Yonghyun Jeong, Haeun Noh, Jungmin Lee, and Jongwon Choi, "Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing", In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025. [Acceptance Rate 24.01% (2,698/11,239)] [Paper] [Github]
- Jungeun Kim*, Jangyeong Jeon, Seungjin Jung, and Junyeong Kim, "De-Bias Using Abstract Meaning Representation for Image Captioning", in Proceedings of IEEE International Conference on Consumer Electronics (ICCE), 2024. [Paper]
- Seungjin Jung*, Seungmo Seo, Yonghyun Jeong, and Jongwon Choi, "Scaling of Class-wise Training Losses for Post-hoc Calibration", in Proceedings of International Conference on Machine Learning (ICML), 2023. [Acceptance Rate 27.94% (1,827/6,538)] [Paper] [Github]
- Junsup Shin*, Youngwook Kang, Seungjin Jung, and Jongwon Choi, “Active Instance Selection for Classification”, IEEE Access. [IF=3.9] 2022 [Paper]

Domestic Paper
- Jongmin Lee, Seungjin Jung, and Jongwon Choi, “Development of Environment- Adaptive Training Method”, Moving Image and Technology (MINT), 2022. [Paper]

Research Project

Advancement of Smart Monitoring System and Identification Technology for Illegal/Defective Food / Sponsored by Ministery of Food and Drug Safety (Jan. 2022 - Now)
Development of Environment-adaptive Training Method for Deep Learning Network / Sponsored by ETRI (Mar. 2021 - Nov. 2021)
Film Production with Deepfake / Sponsored by Bk21 (Jan. 2021 - Mar. 2021)
Development of AI System / Sponsored by Doosan (Sep. 2020 - Dec. 2020)

Invited Talk

Artificial Intelligence Graduate School Symposium, oral presentation (Aug. 2023)

Patent

Registration

[KR1] 10-2650992. Apparatus and Method for Neural Network Compression using Block Transform (Jun. 2024)
[KR2] 10-2695536. Irregular/Bad Food Monitoring Device and Method (Aug. 2024)
[KR3] 10-2695889. Method and apparatus for controlling loss scale by class for post-correction, and computer program (Aug. 2024)
[KR4] 10-2724394. Method and apparatus for analyzing articles through keyword extraction, and computer programs (Oct. 2024)

Application

[US1] 18/396,927. Method and apparatus for controlling loss scale by class for post-correction, and computer program (Dec. 2023)

Peer-review Activity

Page updated

Report abuse