Limb Prescribe: Text-to-Pose Generative Model for Therapeutic Exercise Prescription
Alsaedi, Shamma
Alsaedi, Shamma
Author
Supervisor
Department
Computer Vision
Embargo End Date
2026-05-21
Type
Thesis
Date
2024
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Despite physical therapy's significant impact on improving quality of life, its high cost often renders it a luxury. This thesis focuses on "Limb Prescribe: Text-to-Pose Generative Model for Therapeutic Exercise Prescription," which aims to make physiotherapy more accessible. Our research began by understanding the domain and identifying areas where AI could add value through multidisciplinary frameworks. We developed Limb Prescribe to address the customization needs of therapeutic exercises. In physiotherapy, each case is unique, with specific needs and constraints. Limb Prescribe is a text-to-pose generative model designed for therapeutic exercise prescriptions. By integrating pose initialization, iterative pose generation based on previous poses, and incorporating physical constraints, we enhance the model's suitability for exercise prescription. Feedback from fifteen physiotherapists confirmed the model's potential, highlighting the need for further development.
Citation
S. Alsaedi, "Limb Prescribe: Text-to-Pose Generative Model for Therapeutic Exercise Prescription", M.S. Thesis, Computer Vision, MBZUAI, Abu Dhabi, UAE, 2024