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

09/28/2020
by   Panwen Hu, et al.
8

Occlusion is still a severe problem in the video-based Re-IDentification (Re-ID) task, which has a great impact on the success rate. The attention mechanism has been proved to be helpful in solving the occlusion problem by a large number of existing methods. However, their attention mechanisms still lack the capability to extract sufficient discriminative information into the final representations from the videos. The single attention module scheme employed by existing methods cannot exploit multi-scale spatial cues, and the attention of the single module will be dispersed by multiple salient parts of the person. In this paper, we propose a Concentrated Multi-grained Multi-Attention Network (CMMANet) where two multi-attention modules are designed to extract multi-grained information through processing multi-scale intermediate features. Furthermore, multiple attention submodules in each multi-attention module can automatically discover multiple discriminative regions of the video frames. To achieve this goal, we introduce a diversity loss to diversify the submodules in each multi-attention module, and a concentration loss to integrate their attention responses so that each submodule can strongly focus on a specific meaningful part. The experimental results show that the proposed approach outperforms the state-of-the-art methods by large margins on multiple public datasets.

READ FULL TEXT

page 1

page 2

page 6

research
09/11/2022

Local-Aware Global Attention Network for Person Re-Identification

Learning representative, robust and discriminative information from imag...
research
04/24/2019

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

Person re-identification becomes a more and more important task due to i...
research
08/04/2021

Multi-Branch with Attention Network for Hand-Based Person Recognition

In this paper, we propose a novel hand-based person recognition method f...
research
09/03/2021

Musical Tempo Estimation Using a Multi-scale Network

Recently, some single-step systems without onset detection have shown th...
research
03/13/2021

Potential Escalator-related Injury Identification and Prevention Based on Multi-module Integrated System for Public Health

Escalator-related injuries threaten public health with the widespread us...
research
08/16/2019

Mixed High-Order Attention Network for Person Re-Identification

Attention has become more attractive in person reidentification (ReID) a...
research
10/15/2019

Attention Network Robustification for Person ReID

The task of person re-identification (ReID) has attracted growing attent...

Please sign up or login with your details

Forgot password? Click here to reset