Computer Vision Lab. conducts research on visual artificial intelligence (AI) that enables computers to understand diverse visual information—such as images, videos, and 3D point clouds—and solve given tasks. In particular, the lab focuses on exploring relationships among objects within visual data, aiming to develop AI systems capable of comprehensive understanding of visual information. This research is being further extended to 3D point clouds and applied to robotics. In addition, the lab plans to pursue a wide range of visual AI research, including multimodal neural networks and neuro-symbolic learning.