CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification

11/19/2018
by   Jiawei Liu, et al.
4

Person re-identification aims to identify the same pedestrian across non-overlapping camera views. Deep learning techniques have been applied for person re-identification recently, towards learning representation of pedestrian appearance. This paper presents a novel Contextual-Attentional Attribute-Appearance Network (CA3Net) for person re-identification. The CA3Net simultaneously exploits the complementarity between semantic attributes and visual appearance, the semantic context among attributes, visual attention on attributes as well as spatial dependencies among body parts, leading to discriminative and robust pedestrian representation. Specifically, an attribute network within CA3Net is designed with an Attention-LSTM module. It concentrates the network on latent image regions related to each attribute as well as exploits the semantic context among attributes by a LSTM module. An appearance network is developed to learn appearance features from the full body, horizontal and vertical body parts of pedestrians with spatial dependencies among body parts. The CA3Net jointly learns the attribute and appearance features in a multi-task learning manner, generating comprehensive representation of pedestrians. Extensive experiments on two challenging benchmarks, i.e., Market-1501 and DukeMTMC-reID datasets, have demonstrated the effectiveness of the proposed approach.

READ FULL TEXT

page 1

page 3

page 4

page 8

research
09/09/2020

Temporal Attribute-Appearance Learning Network for Video-based Person Re-Identification

Video-based person re-identification aims to match a specific pedestrian...
research
04/14/2021

Graph-based Person Signature for Person Re-Identifications

The task of person re-identification (ReID) is to match images of the sa...
research
08/27/2019

Unsupervised Domain-Adaptive Person Re-identification Based on Attributes

Pedestrian attributes, e.g., hair length, clothes type and color, locall...
research
02/27/2019

Attributes-aided Part Detection and Refinement for Person Re-identification

Person attributes are often exploited as mid-level human semantic inform...
research
07/22/2013

Appearance Descriptors for Person Re-identification: a Comprehensive Review

In video-surveillance, person re-identification is the task of recognisi...
research
06/21/2022

KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing

Part-level attribute parsing is a fundamental but challenging task, whic...
research
11/20/2018

Sequence-based Person Attribute Recognition with Joint CTC-Attention Model

Attribute recognition has become crucial because of its wide application...

Please sign up or login with your details

Forgot password? Click here to reset