Recurrent Attention Models for Depth-Based Person Identification

Abstract

We present an attention-based model that reasons on human body shape and motion dynamics to identify individuals in the absence of RGB information, hence in the dark. Our approach leverages unique 4D spatio-temporal signatures to address the identification problem across days. Formulated as a reinforcement learning task, our model is based on a combination of convolutional and recurrent neural networks with the goal of identifying small, discriminative regions indicative of human identity. We demonstrate that our model produces state-of-the-art results on several published datasets given only depth images. We further study the robustness of our model towards viewpoint, appearance, and volumetric changes. Finally, we share insights gleaned from interpretable 2D, 3D, and 4D visualizations of our model's spatio-temporal attention.

DOI: 10.1109/CVPR.2016.138

Extracted Key Phrases

9 Figures and Tables

0102020162017
Citations per Year

Citation Velocity: 11

Averaging 11 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@article{Haque2016RecurrentAM, title={Recurrent Attention Models for Depth-Based Person Identification}, author={Albert Haque and Alexandre Alahi and Fei-fei Li}, journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2016}, pages={1229-1238} }