Research Homepage | Jongseo Lee

🧑‍💻 About Me

Jongseo Lee

🎓 M.S. Student in Computer Science

🏛 Kyung Hee University

🔬 Vision and Learning Lab, Advised by Prof. Jinwoo Choi

📧 jong980812@khu.ac.kr

🎓 Education

📌 B.S. in Biomedical Engineering, Kyung Hee University (2017 – 2023.2)
📌 B.S. in Electronics Engineering, Kyung Hee University (2020 – 2023.7)
📌 M.S. in Computer Science, Kyung Hee University (2023.8 – Present)

Hello! I am currently pursuing a Master’s degree in Computer Science at Kyung Hee University, with one semester remaining until graduation.

Prior to my graduate studies, I earned dual bachelor's degrees in Biomedical Engineering and Electronics Engineering. This interdisciplinary background has given me a strong foundation in signal processing, embedded systems, and AI, which I now integrate into my research.

My research is conducted at the Vision and Learning Lab under Professor Jinwoo Choi, where I specialize in Video Understanding. I am particularly focused on:

🎥 Video Action Recognition – Developing AI models that can accurately interpret human actions in videos.
📝 Video-Text Multimodal Learning – Integrating textual and visual information for richer video understanding.
🔍 Explainable AI (XAI) for Video Analysis – Making AI decisions more interpretable and trustworthy.

Recent, I am deeply passionate about Video-eXplainable-AI and Video-Text multimodal learning . I am always open to collaboration and discussions on cutting-edge research in Computer Vision, Multimodal AI, and Explainability.

Feel free to connect with me! 🚀

✉️ Contact

Email: jong980812@khu.ac.kr

📄 Publications

* indicates equally contributed first authors

† indicates corresponding author

PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition

Authors: Jongseo Lee, Wooil Lee, Gyeong-Moon Park†, Seong Tae Kim†, Jinwoo Choi†

Conference: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2025

CA²ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition

Authors: Jongseo Lee*, Joohyun Chang*, Dongho Lee, Jinwoo Choi†

Preprint: arXiv 2025 (IEEE Transactions on Pattern Analysis and Machine Intelligence under review)

Video Concept Bottleneck Model

Authors: Jongseo Lee, Soohyun Park, Jinwoo Choi†

Conference: Korean Institute of Information Scientists and Engineers, 2024

PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond

Authors: Jongseo Lee*, Geo Ahn*, Seong Tae Kim†, Jinwoo Choi†

Preprint: arXiv 2024 (under review)

CAST: Cross-Attention in Space and Time for Video Action Recognition

Authors: Dongho Lee*, Jongseo Lee*, Jinwoo Choi†

Conference: NeurIPS 2023

Efficient Video Class Incremental Learning via Class Token Re-Learning

Authors: Jongseo Lee, Soohyun Park, Jinwoo Choi†

Conference: Korean Institute of Information Scientists and Engineers (KIISE), 2024

Audio-Video Cross Attention for Effective Video Action Recognition

Authors: Jongseo Lee, Joohyun Chang, Jinwoo Choi†

Conference: Korean Institute of Information Scientists and Engineers (KIISE), 2024

Metaverse Interface with Haptic and Rigid Sense Feedback at a Low Cost

Authors: Jongseo Lee, Su Hyeon Kim, Sun Woong Jang, Jun Yeong Moon, Doug Young Suh†

Journal: Journal of Appropriate Technology, Volume 8(2), 2022

DOI: 10.37675/jat.2022.00171