Person re-identification with intra-domain similarity grouping based on semantic fusion

Unsupervised cross-domain person re-identification aims to adapt a model trained on a labeled source-domain dataset to a target-domain dataset.However, the cluster-based unsupervised cross-domain pedestrian re-identification algorithm often generates noise due to the different input pedestrian pictu...

Полное описание

Библиографические подробности

Главные авторы:	Qiqi KOU, Ji HUANG, Deqiang CHENG, Yunlong LI, Jianying ZHANG
Формат:	Artigo
Язык:	Chinês
Опубликовано:	Editorial Department of Journal on Communications 2022-07-01
Серии:	Tongxin xuebao
Предметы:	unsupervised cross domain;person re-identification;semantic fusion;adaptive perception;fine-grained information
Online-ссылка:	http://www.joconline.com.cn/thesisDetails#10.11959/j.issn.1000-436x.2022136
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!