Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/122930
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification
Author: Wei, X.
Zhang, C.
Liu, L.
Shen, C.
Wu, J.
Citation: Proceedings of the 14th Asian Conference on Computer Vision (ACCV 2018), as published in Lecture Notes in Computer Science, 2019 / vol.11362, pp.575-591
Publisher: Springer
Publisher Place: Switzerland
Issue Date: 2019
Series/Report no.: Lecture Notes in Computer Science; 11362
ISBN: 9783030208899
ISSN: 0302-9743
1611-3349
Conference Name: Asian Conference on Computer Vision (ACCV) (02 Dec 2018 - 06 Dec 2018 : Perth, Australia)
Statement of
Responsibility: 
Xiu-Shen Wei, B, Chen-Lin Zhang, Lingqiao Liu, Chunhua Shen, and Jianxin Wu
Abstract: Vehicle re-identification is an important problem and becomes desirable with the rapid expansion of applications in video surveillance and intelligent transportation. By recalling the identification process of human vision, we are aware that there exists a native hierarchical dependency when humans identify different vehicles. Specifically, humans always firstly determine one vehicle’s coarse-grained category, i.e., the car model/type. Then, under the branch of the predicted car model/type, they are going to identify specific vehicles by relying on subtle visual cues, e.g., customized paintings and windshield stickers, at the fine-grained level. Inspired by the coarse-to-fine hierarchical process, we propose an end-to-end RNN-based Hierarchical Attention (RNN-HA) classification model for vehicle re-identification. RNN-HA consists of three mutually coupled modules: the first module generates image representations for vehicle images, the second hierarchical module models the aforementioned hierarchical dependent relationship, and the last attention module focuses on capturing the subtle visual information distinguishing specific vehicles from each other. By conducting comprehensive experiments on two vehicle re-identification benchmark datasets VeRi and VehicleID, we demonstrate that the proposed model achieves superior performance over state-of-the-art methods.
Keywords: Vehicle re-identification; Hierarchical dependency; Attention mechanism; Deep learning
Rights: © Springer Nature Switzerland AG 2019
RMID: 0030119608
DOI: 10.1007/978-3-030-20890-5_37
Grant ID: http://purl.org/au-research/grants/arc/DE170101259
Published version: https://link.springer.com/book/10.1007/978-3-030-20890-5
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.