@inproceedings{he2018a,
author = {He, Anfeng and Luo, Chong and Tian, Xinmei and Zeng, Wenjun},
title = {A Twofold Siamese Network for Real-Time Object Tracking},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2018},
month = {June},
abstract = {Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similarity learning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addition, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed according to the channel activations around the target position. While the inherited architecture from SiamFC allows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outperforms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks.},
publisher = {IEEE},
url = {http://approjects.co.za/?big=en-us/research/publication/twofold-siamese-network-real-time-object-tracking/},
edition = {Conference on Computer Vision and Pattern Recognition},
}