跟踪(教育)
计算机视觉
对偶(语法数字)
BitTorrent跟踪器
视频跟踪
跟踪系统
注意力网络
凝视
作者
Lei Pu,Xinxi Feng,Zhiqiang Hou,Wangsheng Yu,Yufei Zha
标识
DOI:10.1016/j.image.2021.116293
摘要
Abstract Fully convolutional Siamese network (SiamFC) has demonstrated high performance in the visual tracking field, but the learned CNN features are redundant and not discriminative to separate the object from the background. To address the above problem, this paper proposes a dual attention module that is integrated into the Siamese network to select the features both in the spatial and channel domains. Especially, a non-local attention module is followed by the last layer of the network, and this benefit to obtain the self-attention feature map of the target from the spatial dimension. On the other hand, a channel attention module is proposed to adjust the importance of different channels’ features according to the corresponding responses generated by each channel feature and the target. Additionally, the GOT10k dataset is employed to train our dual attention Siamese network (SiamDA) to improve the target representation ability, which enhances the discrimination of the model. Experimental results show that the proposed algorithm improves the accuracy by 7.6% and the success rate by 5.6% compared with the baseline tracker.
科研通智能强力驱动
Strongly Powered by AbleSci AI