File(s) under permanent embargo
End-to-end correspondence and relationship learning of mid-level deep features for person re-identification
© 2017 IEEE. In this paper, a unified deep convolutional architecture is proposed to address the problems in the person re-identification task. The proposed method adaptively learns the discriminative deep mid-level features of a person and constructs the correspondence features between an image pair in a data-driven manner. The previous Siamese structure deep learning approaches focus only on pair-wise matching between features. In our method, we consider the latent relationship between mid-level features and propose a network structure to automatically construct the correspondence features from all input features without a pre-defined matching function. The experimental results on three benchmarks VIPeR, CUHK01 and CUHK03 show that our unified approach improves over the previous state-of-the-art methods.
History
Event
Digital Image Computing: Techniques and Applications. Conference (2017 : Sydney, New South Wales)Pagination
1 - 6Publisher
IEEELocation
Sydney, New South WalesPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2017-11-29End date
2017-12-01ISBN-13
9781538628393Language
engPublication classification
E1 Full written paper - refereedTitle of proceedings
DICTA 2017 : Proceedings of the International Conference on Digital Image Computing: Techniques and ApplicationsUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC