CVNov 12, 2025

Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition

arXiv:2511.09388v11 citationsh-index: 41Has Code
Originality Incremental advance
AI Analysis

This work addresses the problem of robust zero-shot action recognition for skeleton-based systems, representing an incremental improvement over existing methods.

The paper tackles the challenge of recognizing unseen skeleton action categories by addressing fragile alignment and rigid classifiers in zero-shot learning, proposing a method that achieves strong performance with only 10% of seen data.

Recognizing unseen skeleton action categories remains highly challenging due to the absence of corresponding skeletal priors. Existing approaches generally follow an "align-then-classify" paradigm but face two fundamental issues, i.e., (i) fragile point-to-point alignment arising from imperfect semantics, and (ii) rigid classifiers restricted by static decision boundaries and coarse-grained anchors. To address these issues, we propose a novel method for zero-shot skeleton action recognition, termed $\texttt{$\textbf{Flora}$}$, which builds upon $\textbf{F}$lexib$\textbf{L}$e neighb$\textbf{O}$r-aware semantic attunement and open-form dist$\textbf{R}$ibution-aware flow cl$\textbf{A}$ssifier. Specifically, we flexibly attune textual semantics by incorporating neighboring inter-class contextual cues to form direction-aware regional semantics, coupled with a cross-modal geometric consistency objective that ensures stable and robust point-to-region alignment. Furthermore, we employ noise-free flow matching to bridge the modality distribution gap between semantic and skeleton latent embeddings, while a condition-free contrastive regularization enhances discriminability, leading to a distribution-aware classifier with fine-grained decision boundaries achieved through token-level velocity predictions. Extensive experiments on three benchmark datasets validate the effectiveness of our method, showing particularly impressive performance even when trained with only 10\% of the seen data. Code is available at https://github.com/cseeyangchen/Flora.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes