AI RESEARCH
BioGait-VLM: A Tri-Modal Vision-Language-Biomechanics Framework for Interpretable Clinical Gait Assessment
arXiv CS.CV
•
ArXi:2603.08564v1 Announce Type: new Video-based Clinical Gait Analysis often suffers from poor generalization as models overfit environmental biases instead of capturing pathological motion. To address this, we propose BioGait-VLM, a tri-modal Vision-Language-Biomechanics framework for interpretable clinical gait assessment. Unlike standard video encoders, our architecture incorporates a Temporal Evidence Distillation branch to capture rhythmic dynamics and a Biomechanical Tokenization branch that projects 3D skeleton sequences into language-aligned semantic tokens.