# StgcDiff: Spatial-Temporal Graph Condition Diffusion for Sign Language Transition Generation

arXiv: https://arxiv.org/abs/2506.13156 · HTML: https://mlsanity.com/paper/2506.13156/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 60 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison](https://mlsanity.com/paper/1910.11006/) (2019)
- [Graph Convolutional Networks for Temporal Action Localization](https://mlsanity.com/paper/1909.03252/) (2019)
- [Progressive Transformers for End-to-End Sign Language Production](https://mlsanity.com/paper/2004.14874/) (2020)
- [Skeleton Aware Multi-modal Sign Language Recognition](https://mlsanity.com/paper/2103.08833/) (2021)
- [SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2104.01528/) (2021)
- [Video-based Sign Language Recognition without Temporal Segmentation](https://mlsanity.com/paper/1801.10111/) (2018)
- [Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition](https://mlsanity.com/paper/2007.14690/) (2020)
- [LLMs are Good Sign Language Translators](https://mlsanity.com/paper/2404.00925/) (2024)
- [Quantitative Survey of the State of the Art in Sign Language Recognition](https://mlsanity.com/paper/2008.09918/) (2020)
- [Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives](https://mlsanity.com/paper/2107.11317/) (2021)
- [FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation](https://mlsanity.com/paper/2403.12962/) (2024)
- [A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2101.00545/) (2021)
- [G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model](https://mlsanity.com/paper/2208.09141/) (2022)
- [Pose-based Sign Language Recognition using GCN and BERT](https://mlsanity.com/paper/2012.00781/) (2020)
- [Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning](https://mlsanity.com/paper/2108.02366/) (2021)
- [Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment](https://mlsanity.com/paper/2312.15645/) (2023)
- [Grid Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2404.00234/) (2024)
- [Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation](https://mlsanity.com/paper/2411.16810/) (2024)
- [Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production](https://mlsanity.com/paper/2412.13609/) (2024)

## Abstract (arXiv)

Sign language transition generation seeks to convert discrete sign language segments into continuous sign videos by synthesizing smooth transitions. However,most existing methods merely concatenate isolated signs, resulting in poor visual coherence and semantic accuracy in the generated videos. Unlike textual languages,sign language is inherently rich in spatial-temporal cues, making it more complex to model. To address this,we propose StgcDiff, a graph-based conditional diffusion framework that generates smooth transitions between discrete signs by capturing the unique spatial-temporal dependencies of sign language. Specifically, we first train an encoder-decoder architecture to learn a structure-aware representation of spatial-temporal skeleton sequences. Next, we optimize a diffusion denoiser conditioned on the representations learned by the pre-trained encoder, which is tasked with predicting transition frames from noise. Additionally, we design the Sign-GCN module as the key component in our framework, which effectively models the spatial-temporal features. Extensive experiments conducted on the PHOENIX14T, USTC-CSL100,and USTC-SLR500 datasets demonstrate the superior performance of our method.