Browse > Computer Vision > Person Re-Identification

Person Re-Identification

122 papers with code · Computer Vision

Person re-identification is the task of associating images of the same person taken from different cameras or from the same camera in different occasions.

( Image credit: PRID2011 dataset )

Leaderboards

Latest papers with code

Pose-guided Visible Part Matching for Occluded Person ReID

1 Apr 2020hh23333/PVPM

Occluded person re-identification is a challenging task as the appearance varies substantially with various obstacles, especially in the crowd scenario.

GRAPH MATCHING PERSON RE-IDENTIFICATION

2
01 Apr 2020

Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification

10 Feb 2020wangguanan/JSIA-ReID

Second, given cross-modality unpaired-images of a person, our method can generate cross-modality paired images from exchanged images.

PERSON RE-IDENTIFICATION

11
10 Feb 2020

Diversity-Achieving Slow-DropBlock Network for Person Re-Identification

9 Feb 2020AI-NERC-NUPT/SDB

In particular, we show that the feature diversity can be well achieved with the use of multiple dropping branches by setting individual dropping ratio for each branch.

PERSON RE-IDENTIFICATION

5
09 Feb 2020

Learning Diverse Features with Part-Level Resolution for Person Re-Identification

21 Jan 2020AI-NERC-NUPT/PLR-OSNet

Learning diverse features is key to the success of person re-identification.

PERSON RE-IDENTIFICATION

2
21 Jan 2020

Deep Learning for Person Re-identification: A Survey and Outlook

13 Jan 2020mangye16/ReID-Survey

The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets.

METRIC LEARNING PERSON RE-IDENTIFICATION REPRESENTATION LEARNING

120
13 Jan 2020

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

6 Jan 2020yxgeee/MMT

In order to mitigate the effects of noisy pseudo labels, we propose to softly refine the pseudo labels in the target domain by proposing an unsupervised framework, Mutual Mean-Teaching (MMT), to learn better features from the target domain via off-line refined hard pseudo labels and on-line refined soft pseudo labels in an alternative training manner.

UNSUPERVISED DOMAIN ADAPTATION UNSUPERVISED PERSON RE-IDENTIFICATION

123
06 Jan 2020

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

ICLR 2020 yxgeee/MMT

In order to mitigate the effects of noisy pseudo labels, we propose to softly refine the pseudo labels in the target domain by proposing an unsupervised framework, Mutual Mean-Teaching (MMT), to learn better features from the target domain via off-line refined hard pseudo labels and on-line refined soft pseudo labels in an alternative training manner.

PERSON RE-IDENTIFICATION UNSUPERVISED DOMAIN ADAPTATION

123
01 Jan 2020

In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation

17 Dec 2019TAMU-VITA/FAT

This work addresses the above two shortcomings of triplet loss, extending its effectiveness to large-scale ReID datasets with potentially noisy labels.

PERSON RE-IDENTIFICATION

18
17 Dec 2019