{"ID":2829796,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11941","arxiv_id":"2512.11941","title":"DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition","abstract":"Zero-shot skeleton-based action recognition (ZS-SAR) is fundamentally constrained by prevailing approaches that rely on aligning skeleton features with static, class-level semantics. This coarse-grained alignment fails to bridge the domain shift between seen and unseen classes, thereby impeding the effective transfer of fine-grained visual knowledge. To address these limitations, we introduce \\textbf{DynaPURLS}, a unified framework that establishes robust, multi-scale visual-semantic correspondences and dynamically refines them at inference time to enhance generalization. Our framework leverages a large language model to generate hierarchical textual descriptions that encompass both global movements and local body-part dynamics. Concurrently, an adaptive partitioning module produces fine-grained visual representations by semantically grouping skeleton joints. To fortify this fine-grained alignment against the train-test domain shift, DynaPURLS incorporates a dynamic refinement module. During inference, this module adapts textual features to the incoming visual stream via a lightweight learnable projection. This refinement process is stabilized by a confidence-aware, class-balanced memory bank, which mitigates error propagation from noisy pseudo-labels. Extensive experiments on three large-scale benchmark datasets, including NTU RGB+D 60/120 and PKU-MMD, demonstrate that DynaPURLS significantly outperforms prior art, setting new state-of-the-art records. The source code is made publicly available at https://github.com/Alchemist0754/DynaPURLS","short_abstract":"Zero-shot skeleton-based action recognition (ZS-SAR) is fundamentally constrained by prevailing approaches that rely on aligning skeleton features with static, class-level semantics. This coarse-grained alignment fails to bridge the domain shift between seen and unseen classes, thereby impeding the effective transfer o...","url_abs":"https://arxiv.org/abs/2512.11941","url_pdf":"https://arxiv.org/pdf/2512.11941v2","authors":"[\"Jingmin Zhu\",\"Anqi Zhu\",\"James Bailey\",\"Jun Liu\",\"Hossein Rahmani\",\"Mohammed Bennamoun\",\"Farid Boussaid\",\"Qiuhong Ke\"]","published":"2025-12-12T10:39:10Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":605970,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2829796,"paper_url":"https://arxiv.org/abs/2512.11941","paper_title":"DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition","repo_url":"https://github.com/Alchemist0754/DynaPURLS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}