{"ID":2829801,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11458","arxiv_id":"2512.11458","title":"Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation","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.","short_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 tha...","url_abs":"https://arxiv.org/abs/2512.11458","url_pdf":"https://arxiv.org/pdf/2512.11458v1","authors":"[\"Jingmin Zhu\",\"Anqi Zhu\",\"Hossein Rahmani\",\"Jun Liu\",\"Mohammed Bennamoun\",\"Qiuhong Ke\"]","published":"2025-12-12T10:53:51Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":605971,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2829801,"paper_url":"https://arxiv.org/abs/2512.11458","paper_title":"Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation","repo_url":"https://github.com/Alchemist0754/Skeleton-Cache","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}