Gait Recognition via Disentangled Representation Learning
This addresses gait recognition for biometric identification, particularly in challenging scenarios with confounding variables like clothing and view angles, but it is incremental as it builds on existing disentanglement and LSTM methods.
The paper tackles the problem of gait recognition by proposing an AutoEncoder framework that disentangles pose and appearance features from RGB imagery, using LSTM to integrate pose features over time, and demonstrates superior performance on CASIA-B, USF, and a new FVG dataset with quantitative gains.
Gait, the walking pattern of individuals, is one of the most important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as the gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and view angle. To remedy this issue, we propose a novel AutoEncoder framework to explicitly disentangle pose and appearance features from RGB imagery and the LSTM-based integration of pose features over time produces the gait feature. In addition, we collect a Frontal-View Gait (FVG) dataset to focus on gait recognition from frontal-view walking, which is a challenging problem since it contains minimal gait cues compared to other views. FVG also includes other important variations, e.g., walking speed, carrying, and clothing. With extensive experiments on CASIA-B, USF and FVG datasets, our method demonstrates superior performance to the state of the arts quantitatively, the ability of feature disentanglement qualitatively, and promising computational efficiency.