Enregistré dans:
Détails bibliographiques
Auteurs principaux: Joseph, Asaf, Peleg, Shmuel
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.10759
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916652336021504
author Joseph, Asaf
Peleg, Shmuel
author_facet Joseph, Asaf
Peleg, Shmuel
contents Clothes-Changing Person Re-Identification (ReID) aims to recognize the same individual across different videos captured at various times and locations. This task is particularly challenging due to changes in appearance, such as clothing, hairstyle, and accessories. We propose a Clothes-Changing ReID method that uses only skeleton data and does not use appearance features. Traditional ReID methods often depend on appearance features, leading to decreased accuracy when clothing changes. Our approach utilizes a spatio-temporal Graph Convolution Network (GCN) encoder to generate a skeleton-based descriptor for each individual. During testing, we improve accuracy by aggregating predictions from multiple segments of a video clip. Evaluated on the CCVID dataset with several different pose estimation models, our method achieves state-of-the-art performance, offering a robust and efficient solution for Clothes-Changing ReID.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10759
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Clothes-Changing Person Re-identification Based On Skeleton Dynamics
Joseph, Asaf
Peleg, Shmuel
Computer Vision and Pattern Recognition
Clothes-Changing Person Re-Identification (ReID) aims to recognize the same individual across different videos captured at various times and locations. This task is particularly challenging due to changes in appearance, such as clothing, hairstyle, and accessories. We propose a Clothes-Changing ReID method that uses only skeleton data and does not use appearance features. Traditional ReID methods often depend on appearance features, leading to decreased accuracy when clothing changes. Our approach utilizes a spatio-temporal Graph Convolution Network (GCN) encoder to generate a skeleton-based descriptor for each individual. During testing, we improve accuracy by aggregating predictions from multiple segments of a video clip. Evaluated on the CCVID dataset with several different pose estimation models, our method achieves state-of-the-art performance, offering a robust and efficient solution for Clothes-Changing ReID.
title Clothes-Changing Person Re-identification Based On Skeleton Dynamics
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.10759