Person Re-identification Meets Image Search

TL;DR

This paper redefines person re-identification as an image search problem, introducing an unsupervised Bag-of-Words approach and a new dataset, achieving faster performance and competitive accuracy.

Contribution

It presents a novel unsupervised Bag-of-Words method for person re-identification and introduces a realistic dataset with distractors, bridging the gap with image search techniques.

Findings

Faster by over two orders of magnitude compared to feature-feature match methods.

Achieves competitive results on three datasets.

Provides a new dataset closer to real-world scenarios.

Abstract

For long time, person re-identification and image search are two separately studied tasks. However, for person re-identification, the effectiveness of local features and the "query-search" mode make it well posed for image search techniques. In the light of recent advances in image search, this paper proposes to treat person re-identification as an image search problem. Specifically, this paper claims two major contributions. 1) By designing an unsupervised Bag-of-Words representation, we are devoted to bridging the gap between the two tasks by integrating techniques from image search in person re-identification. We show that our system sets up an effective yet efficient baseline that is amenable to further supervised/unsupervised improvements. 2) We contribute a new high quality dataset which uses DPM detector and includes a number of distractor images. Our dataset reaches closer to realistic settings, and new perspectives are provided. Compared with approaches that rely on feature-feature match, our method is faster by over two orders of magnitude. Moreover, on three datasets, we report competitive results compared with the state-of-the-art methods.