Zoom-RNN: A Novel Method for Person Recognition Using Recurrent Neural Networks

TL;DR

Zoom-RNN introduces a recurrent neural network-based approach that combines cues from multiple body regions to improve person recognition accuracy in unconstrained social media photos.

Contribution

The paper presents Zoom-RNN, a novel method that leverages evidence from different body regions for person recognition, outperforming traditional fusion techniques.

Findings

Improved recognition accuracy on PIPA dataset.

Effective integration of multi-region cues using RNNs.

Outperforms conventional fusion methods.

Abstract

The overwhelming popularity of social media has resulted in bulk amounts of personal photos being uploaded to the internet every day. Since these photos are taken in unconstrained settings, recognizing the identities of people among the photos remains a challenge. Studies have indicated that utilizing evidence other than face appearance improves the performance of person recognition systems. In this work, we aim to take advantage of additional cues obtained from different body regions in a zooming in fashion for person recognition. Hence, we present Zoom-RNN, a novel method based on recurrent neural networks for combining evidence extracted from the whole body, upper body, and head regions. Our model is evaluated on a challenging dataset, namely People In Photo Albums (PIPA), and we demonstrate that employing our system improves the performance of conventional fusion methods by a noticeable margin.