@ Inha University
Notice
We are currently seeking MS/PhD students with a strong interest in video understanding (e.g., retrieval and grounding).
If you are interested in joining our team, please contat us at pilhyeon [dot] lee [at] inha [dot] ac [dot] kr.
Our research focuses primarily on understanding and how to interactively fuse multimodal information from diverse sources such as images, videos, text, audio, and etc. Specfically, our research topics cover various problems of Computer Vision (CV), Natural Languge Processing (NLP), and Signal Processing (SP), which includes (but not limited to):
Vision & Language
Scene Understanding (e.g., detection, segmentation)
Cross-modal Retrieval (e.g., text-to-image, audio-to-video)
Video Understanding
Human Behavior Analysis
Knowledge Distillation
Large-scale Foundation Models (e.g., LLMs, LVMs)
Generative Models
Model Robustness
Semi- / Weakly-supervised Learning
Model Debiasing & Fairness