Neural Person Search Machines

TL;DR

This paper introduces Neural Person Search Machines (NPSM), a recursive neural approach that progressively refines search regions for person identification, leveraging query and contextual cues to improve accuracy.

Contribution

The paper presents a novel recursive neural framework for person search that adaptively narrows search regions and uses internal memory to enhance robustness and precision.

Findings

Outperforms state-of-the-art methods on CUHK-SYSU dataset.

Achieves higher mAP and top-1 accuracy on PRW dataset.

Demonstrates effective recursive localization in person search.

Abstract

We investigate the problem of person search in the wild in this work. Instead of comparing the query against all candidate regions generated in a query-blind manner, we propose to recursively shrink the search area from the whole image till achieving precise localization of the target person, by fully exploiting information from the query and contextual cues in every recursive search step. We develop the Neural Person Search Machines (NPSM) to implement such recursive localization for person search. Benefiting from its neural search mechanism, NPSM is able to selectively shrink its focus from a loose region to a tighter one containing the target automatically. In this process, NPSM employs an internal primitive memory component to memorize the query representation which modulates the attention and augments its robustness to other distracting regions. Evaluations on two benchmark datasets, CUHK-SYSU Person Search dataset and PRW dataset, have demonstrated that our method can outperform current state-of-the-arts in both mAP and top-1 evaluation protocols.