# Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition

arXiv: https://arxiv.org/abs/2411.10745 · HTML: https://mlsanity.com/paper/2411.10745/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 64 of its 80 references that are in the map.
- First posted on arXiv 16 Nov 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction](https://mlsanity.com/paper/2409.18124/) (2024)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)

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

- [Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens](https://mlsanity.com/paper/2502.16175/) (2025)
- [Universal Skeleton Understanding via Differentiable Rendering and MLLMs](https://mlsanity.com/paper/2603.18003/) (2026)
- [The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models](https://mlsanity.com/paper/2601.08876/) (2026)
- [Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2604.09063/) (2026)
- [SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2604.02222/) (2026)
- [Toward Universal Skeleton-Based Action Recognition across Heterogeneous Skeletons and Open Vocabularies](https://mlsanity.com/paper/2604.17013/) (2026)
- [PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition](https://mlsanity.com/paper/2605.11497/) (2026)
- [Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach](https://mlsanity.com/paper/2607.00716/) (2026)
- [Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2608.04623/) (2026)

## Abstract (arXiv)

In zero-shot skeleton-based action recognition (ZSAR), aligning skeleton features with the text features of action labels is essential for accurately predicting unseen actions. ZSAR faces a fundamental challenge in bridging the modality gap between the two-kind features, which severely limits generalization to unseen actions. Previous methods focus on direct alignment between skeleton and text latent spaces, but the modality gaps between these spaces hinder robust generalization learning. Motivated by the success of diffusion models in multi-modal alignment (e.g., text-to-image, text-to-video), we firstly present a diffusion-based skeleton-text alignment framework for ZSAR. Our approach, Triplet Diffusion for Skeleton-Text Matching (TDSM), focuses on cross-alignment power of diffusion models rather than their generative capability. Specifically, TDSM aligns skeleton features with text prompts by incorporating text features into the reverse diffusion process, where skeleton features are denoised under text guidance, forming a unified skeleton-text latent space for robust matching. To enhance discriminative power, we introduce a triplet diffusion (TD) loss that encourages our TDSM to correct skeleton-text matches while pushing them apart for different action classes. Our TDSM significantly outperforms very recent state-of-the-art methods with significantly large margins of 2.36%-point to 13.05%-point, demonstrating superior accuracy and scalability in zero-shot settings through effective skeleton-text matching.