AI & Media Lab
Research Topics
Multimodal Learning
combines text, images, audio, and video to accommodate various learning preferences, enhancing overall comprehension
Domain Transfer
adapts an AI model from one domain to another, enhancing its performance on related but different data distributions
Scene Understanding
aims to interpret a visual scene, recognizing objects, their relationships, and the context to interact intelligently with their environment
Parameter-Efficient Fine-Tuning
optimizes an AI model using a small subset of its parameters while minimizing computational costs
and memory usage
3D Vision
refers to the process of extracting spatial information from visual input, enabling machines to perceive and navigate the 3D world
Robot Vision
enables robots to understand visual data from their surroundings using cameras and multiple sensors, enhancing their autonomy and versatility
4
On-going Projects
10
Research Members
20
Journal Publications
32
Conference Publications
AI & Media Lab (AIM Lab)
Office : 90313, International Hall, Sungkyunkwan University,
25-2 Sungkyunkwan-ro, Jongno-gu, Seoul 03063, Korea
Email : csehong@skku.edu Web : aim.skku.edu Tel : 02-740-1809