Group Re-Identification with Group Context Graph Neural Networks
Document Type
Article
Publication Title
IEEE Transactions on Multimedia
Abstract
Group re-identification aims to match groups of people across disjoint cameras. In this task, the contextual information from neighbor individuals can be exploited for re-identifying each individual within the group as well as the entire group. However, compared with single person re-identification, it brings new challenges including group layout and group membership changes. Motivated by the observation that individuals who are close together are more likely to keep in the same group under different cameras than those who are far apart, we propose to model each group as a spatial K-nearest neighbor graph (SKNNG) and design a group context graph neural network (GCGNN) for graph representation learning. Specifically, for each node in the graph, the proposed GCGNN learns an embedding which aggregates the contextual information from neighbor nodes. We design multiple weighting kernels for neighborhood aggregation based on the graph properties including node in-degrees and spatial relationship attributes. We compute the similarity scores between node embeddings of two graphs for group member association and obtain the matching score between the two graphs by summing up the similarity scores of all linked node pairs. Experimental results on three public datasets show that our approach performs favorably against state-of-the-art methods and achieves high efficiency.
First Page
2614
Last Page
2626
DOI
10.1109/TMM.2020.3013531
Publication Date
1-1-2021
Keywords
group context graph neural network, Group re-identification, spatial K-NN graph
Recommended Citation
J. Zhu et al., "Group Re-Identification with Group Context Graph Neural Networks," IEEE Transactions on Multimedia, vol. 23, pp. 2614 - 2626, Jan 2021.
The definitive version is available at https://doi.org/10.1109/TMM.2020.3013531