# Fusing Biomechanical and Spatio-Temporal Features for Fall Prediction: Characterizing and Mitigating the Simulation-to-Reality Gap

arXiv: https://arxiv.org/abs/2511.14620 · HTML: https://mlsanity.com/paper/2511.14620/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 56 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [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)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Deep Learning for Sensor-based Activity Recognition: A Survey](https://mlsanity.com/paper/1707.03502/) (2017)
- [BlazePose: On-device Real-time Body Pose tracking](https://mlsanity.com/paper/2006.10204/) (2020)
- [Uncertainty-Aware Attention for Reliable Interpretation and Prediction](https://mlsanity.com/paper/1805.09653/) (2018)
- [Multi Visual Modality Fall Detection Dataset](https://mlsanity.com/paper/2206.12740/) (2022)

## Abstract (arXiv)

Falls are a leading cause of injury and loss of independence among older adults. Vision-based fall prediction systems offer a non-invasive solution to anticipate falls seconds before impact, but their development is hindered by the scarcity of available fall data. Contributing to these efforts, this study proposes the Biomechanical Spatio-Temporal Graph Convolutional Network (BioST-GCN), a dual-stream model that combines both pose and biomechanical information using a cross-attention fusion mechanism. Our model outperforms the vanilla ST-GCN baseline by 5.32% and 2.91% F1-score on the simulated MCF-UA stunt-actor and MUVIM datasets, respectively. The spatio-temporal attention mechanisms in the ST-GCN stream also provide interpretability by identifying critical joints and temporal phases. However, a critical simulation-reality gap persists. While our model achieves an 89.0% F1-score with full supervision on simulated data, zero-shot generalization to unseen subjects drops to 35.9%. This performance decline is likely due to biases in simulated data, such as 'intent-to-fall' cues. For older adults, particularly those with diabetes or frailty, this gap is exacerbated by their unique kinematic profiles. To address this, we propose personalization strategies and advocate for privacy-preserving data pipelines to enable real-world validation. Our findings underscore the urgent need to bridge the gap between simulated and real-world data to develop effective fall prediction systems for vulnerable elderly populations.