Learning comprehensive global features in person re-identification: Ensuring discriminativeness of more local regions
Authors:
- Jiali XiJXJiali Xi
- Jianqiang HuangJHJianqiang Huang
- Shibao ZhengSZShibao Zheng
- Qin ZhouQZQin Zhou
- Bernt SchieleBSBernt Schiele
- Xian-Sheng HuaXHXian-Sheng Hua
- Qianru SunQSQianru Sun
- 24 September 2022
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 134
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62071292, U21B2013)
- Ministry of Education of the People's Republic of China
- Agency for Science, Technology and Research (A20E6c0101)
- Ministry of Education - Singapore
This publication has 13 references indexed in Scilit:
- Part-guided graph convolution networks for person re-identificationPattern Recognition, 2021
- MEMF: Multi-level-attention embedding and multi-layer-feature fusion model for person re-identificationPattern Recognition, 2021
- Dual-path Convolutional Image-Text Embeddings with Instance LossACM Transactions on Multimedia Computing, Communications, and Applications, 2020
- Deep-Person: Learning discriminative deep features for person Re-IdentificationPattern Recognition, 2020
- A Strong Baseline and Batch Normalization Neck for Deep Person Re-IdentificationIEEE Transactions on Multimedia, 2019
- Improving person re-identification by attribute and identity learningPattern Recognition, 2019
- SphereReID: Deep hypersphere manifold embedding for person re-identificationJournal of Visual Communication and Image Representation, 2019
- Deep Representation Learning With Part Loss for Person Re-IdentificationIEEE Transactions on Image Processing, 2019
- A Discriminatively Learned CNN Embedding for Person ReidentificationACM Transactions on Multimedia Computing, Communications, and Applications, 2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017