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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yang, Li, Miaoge, Rao, Zhijie, Zeng, Deze, Guo, Song, Guo, Jingcai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915904774733824
author Chen, Yang
Li, Miaoge
Rao, Zhijie
Zeng, Deze
Guo, Song
Guo, Jingcai
author_facet Chen, Yang
Li, Miaoge
Rao, Zhijie
Zeng, Deze
Guo, Song
Guo, Jingcai
contents 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, \textit{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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_09388
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
Chen, Yang
Li, Miaoge
Rao, Zhijie
Zeng, Deze
Guo, Song
Guo, Jingcai
Computer Vision and Pattern Recognition
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, \textit{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.
title Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.09388