From Face to Gait: Weakly-Supervised Learning of Gender Information from Walking Patterns
This addresses the limitation of facial analysis for gender inference in real-world surveillance or monitoring applications where faces are not visible, though it is incremental as it builds on existing gait and facial analysis methods.
The paper tackles the problem of inferring gender from video when facial features are unavailable by learning from walking patterns, achieving an F1 score of 91% and generalizing to scenarios where faces are obstructed or not facing the camera.
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.