From Face to Gait: Weakly-Supervised Learning of Gender Information from Walking Patterns

TL;DR

This paper introduces a weakly-supervised approach to infer gender from walking patterns, overcoming limitations of facial analysis in obstructed or non-frontal views, achieving high accuracy and generalization.

Contribution

It presents a novel gait-based gender inference method that leverages facial analysis for annotation and propagates labels to unseen angles, enhancing robustness in real-world scenarios.

Findings

Achieves an F1 score of 91% in gender classification.

Successfully generalizes to non-frontal and obstructed face scenarios.

Outperforms or matches facial analysis models in challenging conditions.

Abstract

Obtaining demographics information from video is valuable for a range of real-world applications. While approaches that leverage facial features for gender inference are very successful in restrained environments, they do not work in most real-world scenarios when the subject is not facing the camera, has the face obstructed or the face is not clear due to distance from the camera or poor resolution. We propose a weakly-supervised method for learning gender information of people based on their manner of walking. We make use of state-of-the art facial analysis models to automatically annotate front-view walking sequences and generalise to unseen angles by leveraging gait-based label propagation. Our results show on par or higher performance with facial analysis models with an F1 score of 91% and the ability to successfully generalise to scenarios in which facial analysis is unfeasible due to subjects not facing the camera or having the face obstructed.