Research
My ultimate research goal is to create AI systems that can support complex tasks in real-life scenarios. To achieve this, I aim to work on advancing multimodal learning to enable AI to seamlessly integrate and understand audio, visual, and language information, improving AI’s perception and interaction with the world.
|
|
Audio Visual Segmentation Through Text Embeddings
Kyungbok Lee,
You Zhang, Zhiyao Duan
ICIP, 2024
arXiv
|
|
A Multi-Stream Fusion Approach with One-Class Learning for Audio-Visual Deepfake Detection
Kyungbok Lee,
You Zhang, Zhiyao Duan
MMSP, 2024
arXiv
|
|
What Variables Affect Out-of-Distribution Generalization in Pretrained Models?
Md Yousuf Harun*,
Kyungbok Lee*
, Jhair Gallardo, Giri Krishnan, Christopher Kanan
NeurIPS, 2024
project page
/
Paper
|
|