Poze: Sports Technique Feedback under Data Constraints

TL;DR

Poze is a novel video processing framework that offers expert-level sports technique feedback by combining pose estimation and sequence comparison, optimized for minimal data, outperforming existing vision-language models in accuracy.

Contribution

Poze introduces a new approach for sports technique feedback that works effectively with limited data, bridging the gap between expert coaching and accessible training.

Findings

Poze achieves 70% higher accuracy than GPT4V.

Poze outperforms LLaVAv1.6 7b by 196%.

Effective with minimal data.

Abstract

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.