Video-Based Convolutional Attention for Person Re-Identification

TL;DR

This paper introduces a video-based person re-identification method using a Siamese network with attention mechanisms at frame and video levels, achieving superior results on a challenging dataset.

Contribution

It presents a novel joint attention framework that processes frame and video information concurrently within a simple architecture for person re-identification.

Findings

Outperforms state-of-the-art on iLIDS-VID dataset

Effective attention mechanisms at frame and video levels

Simple yet powerful architecture

Abstract

In this paper we consider the problem of video-based person re-identification, which is the task of associating videos of the same person captured by different and non-overlapping cameras. We propose a Siamese framework in which video frames of the person to re-identify and of the candidate one are processed by two identical networks which produce a similarity score. We introduce an attention mechanisms to capture the relevant information both at frame level (spatial information) and at video level (temporal information given by the importance of a specific frame within the sequence). One of the novelties of our approach is given by a joint concurrent processing of both frame and video levels, providing in such a way a very simple architecture. Despite this fact, our approach achieves better performance than the state-of-the-art on the challenging iLIDS-VID dataset.