About Me
Hi! I am a Ph.D. student at SNU Computer Vision Lab, under the guidance of Prof. Bohyung Han. My research interest is in computer vision and machine learning, with a primary focus on object and scene understanding from videos including tasks like action recognition and object tracking. Recently, I have been interested in adapting foundational multi-modal models for video understanding while preserving their generalization ability.
In addition to my research, I am also passionate about promoting diversity and accessibility in AI. My vision is to create a world where technology is accessible to all, including individuals with disabilities and those from underrepresented racial and gender groups.
Here is my CV for more info!
Contact: minji@snu.ac.kr
🔥 News
- April 2024: Our paper on leveraging CLIP for video recognition has been arxived.
- October 2023: I joined NAVER AI Lab as a research intern.
- July 2022: Our paper on resolving training/testing inconsistency problem in visual tracking has been accepted at ECCV 2022.
- April 2022: Our paper on online hybrid lightweight representation learning for visual tracking has been accepted at IJCAI 2022.
📝 Publications
Leveraging Temporal Contextualization for Video Action Recognition
Minji Kim, Dongyoon Han, Taekyung Kim, Bohyung Han
arXiv 2024, under review | [Code]
Towards Sequence-Level Training for Visual Tracking
Minji Kim*, Seungkwan Lee*, Jungseul Ok, Bohyung Han, Minsu Cho (*Equal Contribution)
ECCV 2022 | [Code]
Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking
Ilchae Jung, Minji Kim, Eunhyeok Park, Bohyung Han
IJCAI 2022
📖 Education
Ph.D. in Electrical and Computer Engineering
Seoul National University
Advisor: Prof. Bohyung Han
Mar 2020 - (now)
B.S. in Electrical and Electronics Engineering
Konkuk University
GPA 4.31/4.50, Class Rank 2/86
Mar 2016 - Feb 2020
💼 Work Experience
NAVER AI Lab
Research Intern
Mentors: Taekyung Kim and Dongyoon Han
Oct 2023 - Mar 2024
🗄 Projects
Tiny Object Detection in EO/IR Images
Agency for Defense Development (ADD)
Jan 2022 - May 2023
🎖 Honors and Awards
IPIU Excellence Paper Award Feb 2023
IPIU Undergraduate Best Paper Award Feb 2019
Intel FPGA Design Contest (3rd Place) Dec 2017
Academic Scholarship, Konkuk University 2016 - 2019
💻 Services
Reviewer
Conference: CVPR 2023, NeurIPS 2023, ICCV 2023, WACV 2024
Journal: TPAMI, MVAP
Teaching Assistant
Dependable Deep Neural Networks SNU 430.659 (Prof. Bohyung Han), Spring 2022
Data Structures SNU 430.217 (Prof. Bohyung Han), Fall 2021
Samsung AI Academy Advanced Course Samsung Electronics, May & July 2020
💪 Leadership
President of BOOT&4DIM
Electronics Engineering Academic Club, Konkuk University, 2018