Neural Person Search Machines
Authors:
- Hao LiuHLHao Liu
- Jiashi FengJFJiashi Feng
- Zequn JieZJZequn Jie
- Karlekar JayashreeKJKarlekar Jayashree
- Bo ZhaoBZBo Zhao
- Meibin QiMQMeibin Qi
- Jianguo JiangJJJianguo Jiang
- Shuicheng YanSYShuicheng Yan
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 493-501
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.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Convolutional Channel Features2015
- Person re-identification by Local Maximal Occurrence representation and metric learning2015
- An improved deep learning architecture for person re-identification2015
- Region-Based Convolutional Networks for Accurate Object Detection and SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Kernelized Relaxed Margin Components Analysis for Person Re-identificationIEEE Signal Processing Letters, 2014
- Fast Feature Pyramids for Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- DeepReID: Deep Filter Pairing Neural Network for Person Re-identification2014
- Unsupervised Salience Learning for Person Re-identification2013
- Large scale metric learning from equivalence constraints2012
- Long Short-Term MemoryNeural Computation, 1997