Multi-Scale Body-Part Mask Guided Attention for Person Re-identification

04/24/2019
by   Honglong Cai, et al.
0

Person re-identification becomes a more and more important task due to its wide applications. In practice, person re-identification still remains challenging due to the variation of person pose, different lighting, occlusion, misalignment, background clutter, etc. In this paper, we propose a multi-scale body-part mask guided attention network (MMGA), which jointly learns whole-body and part body attention to help extract global and local features simultaneously. In MMGA, body-part masks are used to guide the training of corresponding attention. Experiments show that our proposed method can reduce the negative influence of variation of person pose, misalignment and background clutter. Our method achieves rank-1/mAP of 95.0 dataset, 89.5 state-of-the-art methods.

READ FULL TEXT

page 1

page 3

page 4

page 7

research
10/18/2017

Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification

Person Re-identification (ReID) is to identify the same person across di...
research
01/21/2020

VMRFANet:View-Specific Multi-Receptive Field Attention Network for Person Re-identification

Person re-identification (re-ID) aims to retrieve the same person across...
research
10/13/2018

Attention Driven Person Re-identification

Person re-identification (ReID) is a challenging task due to arbitrary h...
research
05/09/2018

Attention-Aware Compositional Network for Person Re-identification

Person re-identification (ReID) is to identify pedestrians observed from...
research
08/11/2021

Person Re-identification via Attention Pyramid

In this paper, we propose an attention pyramid method for person re-iden...
research
09/28/2020

Concentrated Multi-Grained Multi-Attention Network for Video Based Person Re-Identification

Occlusion is still a severe problem in the video-based Re-IDentification...
research
06/17/2020

Cross-Correlated Attention Networks for Person Re-Identification

Deep neural networks need to make robust inference in the presence of oc...

Please sign up or login with your details

Forgot password? Click here to reset