Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/108887
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Person re-identification via recurrent feature aggregation |
Author: | Yan, Y. Ni, B. Song, Z. Ma, C. Yan, Y. Yang, X. |
Citation: | Lecture Notes in Artificial Intelligence, 2016 / Leibe, B., Matas, J., Sebe, N., Welling, M. (ed./s), pp.701-716 |
Publisher: | Springer |
Issue Date: | 2016 |
Series/Report no.: | Lecture Notes in Computer Science; 9910 |
ISBN: | 9783319464657 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | 14th European Conference on Computer Vision (ECCV 2016) (11 Oct 2016 - 14 Oct 2016 : Amsterdam, The Netherlands) |
Editor: | Leibe, B. Matas, J. Sebe, N. Welling, M. |
Statement of Responsibility: | Yichao Yan, Bingbing Ni, Zhichao Song, Chao Ma, Yan Yan, and Xiaokang Yang |
Abstract: | We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches. This is in contrast to previous person re-id works, which rely on either single frame based person to person patch matching, or graph based sequence to sequence matching. We show that a progressive/sequential fusion framework based on long short term memory (LSTM) network aggregates the frame-wise human region representation at each time stamp and yields a sequence level human feature representation. Since LSTM nodes can remember and propagate previously accumulated good features and forget newly input inferior ones, even with simple hand-crafted features, the proposed recurrent feature aggregation network (RFA-Net) is effective in generating highly discriminative sequence level human representations. Extensive experimental results on two person re-identification benchmarks demonstrate that the proposed method performs favorably against state-of-the-art person re-identification methods. |
Keywords: | Person re-identification; feature fusion; long short term memory networks |
Rights: | © Springer International Publishing AG 2016 |
DOI: | 10.1007/978-3-319-46466-4_42 |
Published version: | http://dx.doi.org/10.1007/978-3-319-46466-4_42 |
Appears in Collections: | Aurora harvest 8 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.