Video Understanding for Activities of Daily Living
Temporal action detection, dense activity recognition, and long-video reasoning over unedited, real-world sequences.
Charlotte Vision Lab
The Charlotte Vision Lab is a computer vision research group at UNC Charlotte focused on building systems that understand and act in the visual world. Our work spans video understanding, multimodal learning, robotic perception, generative modeling, and trustworthy machine vision. Our goal is to build trustworthy systems that can perceive, reason, and assist in complex real-world environments.
Research
Our Research Directions
Vision-Language and Vision-Language-Action Models
Visual question answering, domain adaptation, interpretable decision-making, and embodied reasoning.
Reliable 3D and Generative Vision
3D scene understanding, controllable image generation, and uncertainty estimation in open-world settings.
Highlights
Selected Publications and Preprints
CVPR 2026
MS-Temba
Temporal modeling for long untrimmed video understanding.
View paperCVPR 2026
Personalized Image Descriptions from Attention Sequences
A method to generate image descriptions in the style of a subject using attention sequences.
View paperCVPR 2025
LLAVIDAL
A multimodal large language vision model for daily activities of living.
View paperPreprint
UniLACT
A depth-aware latent action framework for vision-language-action models in robot learning.
View paper