# Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment

arXiv: https://arxiv.org/abs/2409.14336 · HTML: https://mlsanity.com/paper/2409.14336/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 57 references that are in the map.
- First posted on arXiv 22 Sep 2024.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [3D Human Action Representation Learning via Cross-View Consistency Pursuit](https://mlsanity.com/paper/2104.14466/) (2021)
- [Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings](https://mlsanity.com/paper/1908.03477/) (2019)
- [Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications](https://mlsanity.com/paper/2003.01455/) (2020)
- [Elaborative Rehearsal for Zero-shot Action Recognition](https://mlsanity.com/paper/2108.02833/) (2021)
- [Revisiting Anchor Mechanisms for Temporal Action Localization](https://mlsanity.com/paper/2008.09837/) (2020)
- [Learning Robust Visual-Semantic Embeddings](https://mlsanity.com/paper/1703.05908/) (2017)
- [Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks](https://mlsanity.com/paper/1704.02581/) (2017)
- [Towards Universal Representation for Unseen Action Recognition](https://mlsanity.com/paper/1803.08460/) (2018)
- [Generative Action Description Prompts for Skeleton-based Action Recognition](https://mlsanity.com/paper/2208.05318/) (2022)
- [MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge](https://mlsanity.com/paper/2303.08914/) (2023)
- [Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition](https://mlsanity.com/paper/2008.03791/) (2020)
- [Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition](https://mlsanity.com/paper/2006.08939/) (2020)
- [Transductive Zero-Shot Action Recognition by Word-Vector Embedding](https://mlsanity.com/paper/1511.04458/) (2015)
- [Zero-Shot Visual Recognition via Bidirectional Latent Embedding](https://mlsanity.com/paper/1607.02104/) (2016)
- [Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2101.11530/) (2021)
- [Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization](https://mlsanity.com/paper/2308.03950/) (2023)
- [Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition](https://mlsanity.com/paper/2406.13327/) (2024)
- [Semantic Embedding Space for Zero-Shot Action Recognition](https://mlsanity.com/paper/1502.01540/) (2015)
- [Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space](https://mlsanity.com/paper/1911.11344/) (2019)
- [Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2404.07487/) (2024)

## Built on by (most cited first, 9 of 9)

- [Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2411.10745/) (2024)
- [Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2511.09388/) (2025)
- [Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2604.09063/) (2026)
- [SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition](https://mlsanity.com/paper/2511.22433/) (2025)
- [Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning](https://mlsanity.com/paper/2508.21363/) (2025)
- [Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition](https://mlsanity.com/paper/2604.17090/) (2026)
- [PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition](https://mlsanity.com/paper/2605.11497/) (2026)
- [GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2608.02236/) (2026)
- [Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2608.04623/) (2026)

## Abstract (arXiv)

Zero-shot action recognition, which addresses the issue of scalability and generalization in action recognition and allows the models to adapt to new and unseen actions dynamically, is an important research topic in computer vision communities. The key to zero-shot action recognition lies in aligning visual features with semantic vectors representing action categories. Most existing methods either directly project visual features onto the semantic space of text category or learn a shared embedding space between the two modalities. However, a direct projection cannot accurately align the two modalities, and learning robust and discriminative embedding space between visual and text representations is often difficult. To address these issues, we introduce Dual Visual-Text Alignment (DVTA) for skeleton-based zero-shot action recognition. The DVTA consists of two alignment modules--Direct Alignment (DA) and Augmented Alignment (AA)--along with a designed Semantic Description Enhancement (SDE). The DA module maps the skeleton features to the semantic space through a specially designed visual projector, followed by the SDE, which is based on cross-attention to enhance the connection between skeleton and text, thereby reducing the gap between modalities. The AA module further strengthens the learning of the embedding space by utilizing deep metric learning to learn the similarity between skeleton and text. Our approach achieves state-of-the-art performances on several popular zero-shot skeleton-based action recognition benchmarks. The code is available at: https://github.com/jidongkuang/DVTA.