Max Robotics — Global Service Robot Directory + US Certification

About

Thi-Lan Le is a computer vision and human-computer interaction researcher whose work centers on gesture and action recognition, skeletal data analysis, and intelligent robotic systems. Her most impactful contribution, "Novel Skeleton-based Action Recognition Using Covariance Descriptors on Most Informative Joints" (2018, 18 citations), introduced an innovative approach to human action recognition by leveraging covariance descriptors on selectively identified skeletal joints, advancing the field's efficiency and accuracy. Building on this, her 2020 work on spatio-temporal representations for skeleton-based recognition further refined methodologies for interpreting human movement from diverse sensor inputs. Le has also made notable strides in hand posture recognition, proposing a kernel-based descriptor framework (2015, 11 citations) with strong applications in sign language interpretation and human-system interaction. Her earlier research into Vietnamese facial expression recognition (2011) demonstrated a commitment to culturally contextual AI development for social robotics. Complementing these efforts, her work on 3D object detection using depth imagery addresses real-world assistive technology challenges. Across her career, Le has consistently bridged theoretical computer vision with practical applications in robotics, surveillance, and accessibility, establishing herself as a meaningful contributor to intelligent human-machine interaction research.