Graph Convolutional Tracking
Abstract
Tracking by siamese networks has achieved favorable performance in recent years. However, most of existing siamese methods do not take full advantage of spatial-temporal target appearance modeling under different contextual situations. In fact, the spatial-temporal information can provide diverse features to enhance the target representation, and the context information is important for online adaption of target localization. To comprehensively leverage the spatial-temporal structure of historical target exemplars and get benefit from the context information, in this work, we present a novel Graph Convolutional Tracking (GCT) method for high-performance visual tracking. Specifically, the GCT jointly incorporates two types of Graph Convolutional Networks (GCNs) into a siamese framework for target appearance modeling. Here, we adopt a spatial-temporal GCN to model the structured representation of historical target exemplars. Furthermore, a context GCN is designed to utilize the context of the current frame to learn adaptive features for target localization. Extensive results on 4 challenging benchmarks show that our GCT method performs favorably against state-of-the-art trackers while running around 50 frames per second.
Cite
Text
Gao et al. "Graph Convolutional Tracking." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00478Markdown
[Gao et al. "Graph Convolutional Tracking." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/gao2019cvpr-graph/) doi:10.1109/CVPR.2019.00478BibTeX
@inproceedings{gao2019cvpr-graph,
title = {{Graph Convolutional Tracking}},
author = {Gao, Junyu and Zhang, Tianzhu and Xu, Changsheng},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.00478},
url = {https://mlanthology.org/cvpr/2019/gao2019cvpr-graph/}
}