SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition
Researchers have developed SkelHCC, a new framework for one-shot action recognition using skeleton data. This approach utilizes hyperbolic geometry to better model the hierarchical structure of human motion and align it with language semantics. The framework also incorporates an LLM-guided cache for efficient inference, demonstrating superior performance on benchmark datasets. AI
IMPACT This framework could improve the accuracy and efficiency of AI systems that interpret human actions from skeletal data, particularly in scenarios with limited training examples.