# Improved visual-information-driven model for crowd simulation and its modular application

arXiv: https://arxiv.org/abs/2504.03758 · HTML: https://mlsanity.com/paper/2504.03758/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 50 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Social Attention: Modeling Attention in Human Crowds](https://mlsanity.com/paper/1710.04689/) (2017)
- [Visual-information-driven model for crowd simulation using temporal convolutional network](https://mlsanity.com/paper/2311.02996/) (2023)

## Built on by (most cited first, 1 of 1)

- [Simulation of collision avoidance behavior in crowd movement by data-driven approach](https://mlsanity.com/paper/2605.31210/) (2026)

## Abstract (arXiv)

Crowd movement simulation is crucial for pedestrian safety management and facility design. Data-driven models offer the potential to improve realism and predictive accuracy, but most are developed for a single scenario, limiting their flexibility. We propose a data-driven crowd simulation model that incorporates refined visual-information extraction and explicit exit cues, aiming to improve flexibility across multiple scenarios by more effectively capturing core navigational features. The model is tested on four fundamental modules (bottleneck, corridor, corner, and T-junction) and further evaluated in a composite scenario using a modular approach. Results show that our model performs well across these scenarios, aligning with pedestrian movement in real-world experiments, and outperforms the classical knowledge-driven model in these scenarios. The research outcomes can provide inspiration for the development of data-driven crowd simulation models and advance the application of data-driven approaches.