Learning Priors of Human Motion With Vision Transformers

Placido Falqueto, Alberto Sanfeliu, Luigi Palopoli, Daniele Fontanelli
1/30/2025
cs.CVcs.RO

No official code found. Best implementation: pla10/IRI_Barcelona (0 stars, last commit 2024-12-06).

Abstract

A clear understanding of where humans move in a scenario, their usual paths and speeds, and where they stop, is very important for different applications, such as mobility studies in urban areas or robot navigation tasks within human-populated environments. We propose in this article, a neural architecture based on Vision Transformers (ViTs) to provide this information. This solution can arguably capture spatial correlations more effectively than Convolutional Neural Networks (CNNs). In the paper, we describe the methodology and proposed neural architecture and show the experiments' results with a standard dataset. We show that the proposed ViT architecture improves the metrics compared to a method based on a CNN.

View on arXivView PDF

Code Implementations(1)

pla10/IRI_BarcelonaCommunity60%

This repository contains the implementation and resources for "Learning Priors of Human Motion With Vision Transformers," a method leveraging Vision Transformers (ViTs) to model and predict human motion. The approach is designed for applications like robotics, mobility studies, and navigation in human-populated environments.

00HTML, PythonFeb 1, 20241 years ago

Similar Papers

Learning Strategies For Successful Crowd Navigation

82% match2024

BrainSLAM: SLAM on Neural Population Activity Data

82% match2024

A causal intervention framework for synthesizing mobility data and evaluating predictive neural networks

81% match2023

Geometric Graph Neural Network Modeling of Human Interactions in Crowded Environments

81% match2024

Deformable Dynamic Convolution for Accurate yet Efficient Spatio-Temporal Traffic Prediction

81% match2025

Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks

80% match1 repo92023

Cite this paper

@article{falqueto2025learning,
  title  = {Learning Priors of Human Motion With Vision Transformers},
  author = {Placido Falqueto and Alberto Sanfeliu and Luigi Palopoli and Daniele Fontanelli},
  year   = {2025},
  eprint = {2501.18543},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.18543v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.18543.svg)](https://codeofpaper.com/paper/2501.18543)

Discussion