Published on Thu Nov 21 2019

Relation Network for Person Re-identification

Hyunjong Park, Bumsub Ham

Person re-identification (reID) aims at retrieving an image of the person of interest from a set of images typically captured by multiple cameras. Using the individual part-level features directly, without considering relations between body parts, confuses differentiating identities of different persons.

0
0
0
Abstract

Person re-identification (reID) aims at retrieving an image of the person of interest from a set of images typically captured by multiple cameras. Recent reID methods have shown that exploiting local features describing body parts, together with a global feature of a person image itself, gives robust feature representations, even in the case of missing body parts. However, using the individual part-level features directly, without considering relations between body parts, confuses differentiating identities of different persons having similar attributes in corresponding parts. To address this issue, we propose a new relation network for person reID that considers relations between individual body parts and the rest of them. Our model makes a single part-level feature incorporate partial information of other body parts as well, supporting it to be more discriminative. We also introduce a global contrastive pooling (GCP) method to obtain a global feature of a person image. We propose to use contrastive features for GCP to complement conventional max and averaging pooling techniques. We show that our model outperforms the state of the art on the Market1501, DukeMTMC-reID and CUHK03 datasets, demonstrating the effectiveness of our approach on discriminative person representations.

Wed Oct 18 2017
Computer Vision
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 multiple cameras. How to extract powerful features is a fundamental problem in ReID and is still an open problem today. We design a Multi-Scale Context-Aware Network to learn powerful features over full body and
0
0
0
Sat Aug 08 2020
Computer Vision
Hierarchical Bi-Directional Feature Perception Network for Person Re-Identification
Previous Person Re-Identification (Re-ID) models aim to focus on the most discriminatory region of an image. Its performance may be compromised when that region is missing caused by camera viewpoint changes or occlusion. We propose a novel model named Hierarchical Bi-directional Feature
0
0
0
Mon Nov 20 2017
Computer Vision
Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
Person re-identification aims at establishing the identity of a pedestrian. We hypothesize that both local and global contextual cues are crucial for an accurate identity matching. We propose a Feature Mask Network (FMN) that takes advantage of ResNet high-level features to predict a feature map mask.
0
0
0
Thu Oct 15 2020
Computer Vision
Integrating Coarse Granularity Part-level Features with Supervised Global-level Features for Person Re-identification
Holistic person re-identification (Re-ID) has achieved great progress respectively in recent years. scenarios in reality often include both holistic and partialPedestrian images. This makes single holistic or partial person Re-ID hard to work with. We propose a robust coarse granularity part-level
0
0
0
Fri Apr 05 2019
Computer Vision
Relation-Aware Global Attention for Person Re-identification
For person re-identification (re-id), attention mechanisms have become more attractive. Previous approaches typically learn attention using local concoctions, ignoring the mining of knowledge from global structure patterns. We propose an effective Relation-Aware Global Attention (RGA) module which captures the global structural information
0
0
0
Fri Nov 29 2019
Computer Vision
Collaborative Attention Network for Person Re-identification
Jointly utilizing global and local features to improve model accuracy is becoming a popular approach for the person re-identification (ReID) problem. Previous works using global features alone have very limited capacity at extracting discriminative local patterns.
0
0
0