CVPR Findings2026
Learning by Neighbor-Aware Semantics, Deciding by Open-Form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
Yang Chen, Miaoge Li, Zhijie Rao, Deze Zeng, Song Guo, Jingcai Guo
Abstract
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 zeroshot skeleton action recognition, termed Flora, which builds upon FlexibLe neighbOr-aware semantic attunement and open-form distRibution-aware flow clAssifier. Specifically, we flexibly attune textual semantics by incorporating neighboring inter-class contextual cues to form directionaware regional semantics, coupled with a cross-modal geometric consistency objective that ensures stable and robust point-to-region alignment. Furthermore, we employ noisefree 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 finegrained 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Scalable Diffusion Models with Transformers cites Learning Transferable Visual Models From Natural Language Supervision
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis cites Scalable Diffusion Models with Transformers
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis cites Learning Transferable Visual Models From Natural Language Supervision
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis cites Flow Matching for Generative Modeling
Builds on23
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
- Scaling Rectified Flow Transformers for High-Resolution Image SynthesisPatrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari et al.ICML 2024 · 3,620 citations
- Fine-Grained Action Retrieval Through Multiple Parts-of-Speech EmbeddingsMichael Wray, Gabriela Csurka, Diane Larlus, Dima DamenICCV 2019 · 185 citations
- Flow Matching for Generative ModelingYaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel et al.ICLR 2023 · 87 citations
Related papers
- SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action RecognitionNing Wang, Tieyue Wu, Naeha Sharif, Farid Boussaïd et al.CVPR 2026 · 3 citations
- Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-Shot Skeleton-Based Action RecognitionJeonghyeok Do, Munchurl KimICCV 2025 · 6 citations
- Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and MaximizationYujie Zhou, Wenwen Qiang, Anyi Rao, Ning Lin et al.ACM MM 2023 · 25 citations
- Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-Based Action RecognitionWenhan Wu, Zhishuai Guo, Chen Chen, Hongfei Xue et al.ICCV 2025 · 4 citations
- Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action RecognitionAnqi Zhu, Jingmin Zhu, James Bailey, Mingming Gong et al.CVPR 2025
