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

MAKE IMPACT

Miaoge Li , Deze Zeng , Song Guo , Jingcai Guo · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2511.09388

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.

Type

preprint

Landing Page

http://arxiv.org/abs/2511.09388

PDF

https://arxiv.org/pdf/2511.09388

OA Status

green

OpenAlex ID

https://openalex.org/W4416223675

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4416223675

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2511.09388

Digital Object Identifier

Title

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

Work title

Type

preprint

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-11-12

Full publication date if available

Authors

Miaoge Li, Deze Zeng, Song Guo, Jingcai Guo

List of authors in order

Landing page

https://arxiv.org/abs/2511.09388

Publisher landing page

PDF URL

https://arxiv.org/pdf/2511.09388

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2511.09388

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload