Relevance Subject Machine: A Novel Person Re-identification Framework

TL;DR

The paper introduces the Relevance Subject Machine, a Bayesian sparse recovery framework for multi-shot person re-identification that effectively handles occlusions and outliers, demonstrating superior performance on standard datasets.

Contribution

It presents a novel Bayesian sparse recovery method with a variational inference approach for multi-shot person re-id, improving accuracy over existing algorithms.

Findings

Achieves 11.5% higher rank 1 accuracy on ILIDS-VID dataset.

Effectively handles occlusions and outliers in re-id videos.

Outperforms state-of-the-art methods on multiple re-id datasets.

Abstract

We propose a novel method called the Relevance Subject Machine (RSM) to solve the person re-identification (re-id) problem. RSM falls under the category of Bayesian sparse recovery algorithms and uses the sparse representation of the input video under a pre-defined dictionary to identify the subject in the video. Our approach focuses on the multi-shot re-id problem, which is the prevalent problem in many video analytics applications. RSM captures the essence of the multi-shot re-id problem by constraining the support of the sparse codes for each input video frame to be the same. Our proposed approach is also robust enough to deal with time varying outliers and occlusions by introducing a sparse, non-stationary noise term in the model error. We provide a novel Variational Bayesian based inference procedure along with an intuitive interpretation of the proposed update rules. We evaluate our approach over several commonly used re-id datasets and show superior performance over current state-of-the-art algorithms. Specifically, for ILIDS-VID, a recent large scale re-id dataset, RSM shows significant improvement over all published approaches, achieving an 11.5% (absolute) improvement in rank 1 accuracy over the closest competing algorithm considered.