@Article{cmes.2022.020471,
AUTHOR = {Jianming Zhang, Kai Wang, Yaoqi He, Lidan Kuang},
TITLE = {Visual Object Tracking via Cascaded RPN Fusion and Coordinate Attention},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {132},
YEAR = {2022},
NUMBER = {3},
PAGES = {909--927},
URL = {http://www.techscience.com/CMES/v132n3/48676},
ISSN = {1526-1506},
ABSTRACT = {Recently, Siamese-based trackers have achieved excellent performance in object tracking. However, the high speed
and deformation of objects in the movement process make tracking difficult. Therefore, we have incorporated
cascaded region-proposal-network (RPN) fusion and coordinate attention into Siamese trackers. The proposed
network framework consists of three parts: a feature-extraction sub-network, coordinate attention block, and
cascaded RPN block.We exploit the coordinate attention block, which can embed location information into channel
attention, to establish long-term spatial location dependence while maintaining channel associations. Thus, the
features of different layers are enhanced by the coordinate attention block. We then send these features separately
into the cascaded RPN for classification and regression. According to the two classification and regression results,
the final position of the target is obtained. To verify the effectiveness of the proposed method, we conducted
comprehensive experiments on the OTB100, VOT2016, UAV123, and GOT-10k datasets. Compared with other
state-of-the-art trackers, the proposed tracker achieved good performance and can run at real-time speed.},
DOI = {10.32604/cmes.2022.020471}
}