Minsu Cho

This study enhances video action detection by focusing on context and classification.

MATR enhances action detection in unedited video streams through memory-augmented technology.

A method to label objects in images without detailed training.

A new approach improves accuracy in 3D pose estimation for machines.

RoDyGS transforms casual videos into realistic dynamic scenes.

A new model combines action segmentation and anticipation for smarter interactions.