TrajViViT: A Trajectory Video Vision Transformer Network for Trajectory Forecasting

Gauthier Rotsart de Hertaing, Dani Manjah, Benoit Macq

2024

Abstract

Forecasting trajectory is a complex task relying on the accuracy of past positions, a correct model of the agent’s motion and an understanding of the social context, which are often challenging to acquire. Deep Neural Networks (DNNs), especially Transformer networks (TFs), have recently evolved as state-of-the-art tools in tackling these challenges. This paper presents TrajViViT (Trajectory Video Vision Transformer), a novel multimodal Transformer Network combining images of the scene and positional information. We show that such approach enhances the accuracy of trajectory forecasting and improves the network’s robustness against inconsistencies and noise in positional data. Our contributions are the design and comprehensive implementation of TrajViViT. A public Github repository will be provided.

Paper Citation

in Harvard Style

Rotsart de Hertaing G., Manjah D. and Macq B. (2024). TrajViViT: A Trajectory Video Vision Transformer Network for Trajectory Forecasting. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 753-760. DOI: 10.5220/0012372000003654

in Bibtex Style

@conference{icpram24,
author={Gauthier Rotsart de Hertaing and Dani Manjah and Benoit Macq},
title={TrajViViT: A Trajectory Video Vision Transformer Network for Trajectory Forecasting},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={753-760},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012372000003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - TrajViViT: A Trajectory Video Vision Transformer Network for Trajectory Forecasting
SN - 978-989-758-684-2
AU - Rotsart de Hertaing G.
AU - Manjah D.
AU - Macq B.
PY - 2024
SP - 753
EP - 760
DO - 10.5220/0012372000003654
PB - SciTePress