Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/162961
Title: Moving towards centers: re-ranking with attention and memory for re-identification
Authors: Zhou, Yunhao
Wang, Yi
Chau, Lap-Pui
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2022
Source: Zhou, Y., Wang, Y. & Chau, L. (2022). Moving towards centers: re-ranking with attention and memory for re-identification. IEEE Transactions On Multimedia, 3161189-. https://dx.doi.org/10.1109/TMM.2022.3161189
Journal: IEEE Transactions on Multimedia 
Abstract: Re-ranking utilizes contextual information to optimize the initial ranking list of person or vehicle re-identification (re-ID), which boosts the retrieval performance at post-processing steps. This paper proposes a re-ranking network to predict the correlations between the probe and top-ranked neighbor samples. Specifically, all the feature embeddings of query and gallery images are expanded and enhanced by a linear combination of their neighbors, with the correlation prediction serves as discriminative combination weights. The combination process is equivalent to moving independent embeddings toward the identity centers, improving cluster compactness. For correlation prediction, we first aggregate the contextual information for probes k-nearest neighbors via the Transformer encoder. Then, we distill and refine the probe-related features into the Contextual Memory cell via attention mechanism. Like humans that retrieve images by not only considering probe images but also memorizing the retrieved ones, the Contextual Memory produces multiview descriptions for each instance. Finally, the neighbors are reconstructed with features fetched from the Contextual Memory, and a binary classifier predicts their correlations with the probe. Experiments on six widely-used person and vehicle re-ID benchmarks demonstrate the effectiveness of the proposed method. Especially, our method surpasses the state-of-the-art re-ranking approaches on large-scale datasets by a significant margin, i.e., with an average 3.08% CMC@1 and 7.46% mAP improvements on VERI-Wild, MSMT17, and VehicleID datasets.
URI: https://hdl.handle.net/10356/162961
ISSN: 1520-9210
DOI: 10.1109/TMM.2022.3161189
Schools: School of Electrical and Electronic Engineering 
Rights: © 2021 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

SCOPUSTM   
Citations 50

6
Updated on Jun 15, 2024

Web of ScienceTM
Citations 50

3
Updated on Oct 26, 2023

Page view(s)

92
Updated on Jun 15, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.