Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

Jingmin Zhu, Anqi Zhu, Hossein Rahmani, Jun Liu, Mohammed Bennamoun, Qiuhong Ke

Keywords: zero-shot learning, generalized zero-shot learning, skeleton-based action recognition, test-time adaptation

TL;DR: We propose a training-free test-time adaptation method that significantly improves zero-shot skeleton action recognition by using a training-free cache model during inference time.

Abstract: We introduce Skeleton-Cache, the first training-free test-time adaptation framework for skeleton-based zero-shot action recognition (SZAR), aimed at improving model generalization to unseen actions during inference. Skeleton-Cache reformulates inference as a lightweight retrieval process over a non-parametric cache that stores structured skeleton representations, combining both global and fine-grained local descriptors. To guide the fusion of descriptor-wise predictions, we leverage the semantic reasoning capabilities of large language models (LLMs) to assign class-specific importance weights. By integrating these structured descriptors with LLM-guided semantic priors, Skeleton-Cache dynamically adapts to unseen actions without any additional training or access to training data. Extensive experiments on NTU RGB+D 60/120 and PKU-MMD II demonstrate that Skeleton-Cache consistently boosts the performance of various SZAR backbones under both zero-shot and generalized zero-shot settings. The code is publicly available at https://github.com/Alchemist0754/Skeleton-Cache.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 6234