Poze: Sports Technique Feedback under Data Constraints
This addresses the economic barrier to expert coaching for sports enthusiasts, offering an accessible alternative.
The paper tackles the problem of providing expert sports technique feedback by introducing Poze, a video processing framework that combines pose estimation with sequence comparison, achieving a 70% increase in accuracy over GPT4V and 196% over LLaVAv1.6 7b in video question-answering tasks.
Access to expert coaching is essential for developing technique in sports, yet economic barriers often place it out of reach for many enthusiasts. To bridge this gap, we introduce Poze, an innovative video processing framework that provides feedback on human motion, emulating the insights of a professional coach. Poze combines pose estimation with sequence comparison and is optimized to function effectively with minimal data. Poze surpasses state-of-the-art vision-language models in video question-answering frameworks, achieving 70% and 196% increase in accuracy over GPT4V and LLaVAv1.6 7b, respectively.