A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking

TL;DR

This paper introduces a pose-sensitive embedding for person re-identification that incorporates pose information into a neural network and proposes a novel, efficient re-ranking method that improves retrieval accuracy without complex computations.

Contribution

It presents a new pose-aware embedding learned via CNNs and a simple, unsupervised re-ranking framework that outperforms existing methods in person re-identification.

Findings

Achieves state-of-the-art re-ranking performance on multiple datasets.

The proposed embedding effectively captures pose information for better discrimination.

The re-ranking method improves retrieval without complex pairwise computations.

Abstract

Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose information of the person to learn a discriminative embedding. In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation. To increase retrieval performance, re-ranking techniques based on computed distances have recently gained much attention. We propose a new unsupervised and automatic re-ranking framework that achieves state-of-the-art re-ranking performance. We show that in contrast to the current state-of-the-art re-ranking methods our approach does not require to compute new rank lists for each image pair (e.g., based on reciprocal neighbors) and performs well by using simple direct rank list based comparison or even by just using the already computed euclidean distances between the images. We show that both our learned representation and our re-ranking method achieve state-of-the-art performance on a number of challenging surveillance image and video datasets. The code is available online at: https://github.com/pse-ecn/pose-sensitive-embedding