Customizing the feature modulation for visual tracking

In visual tracking, the target always undergoes appearance variations due to a variety of challenging situations, such as deformation and rotation. In this paper, we propose the target-guided feature modulation network based on siamese network to extract the more target-relevant features, which is guided by a template to modulate the search features that can be directly used for classification and localization. Specifically, we customize two target-guided feature modulation subnetworks for visual tracking, which are called template-guided spatial-attention modulation subnetwork and template-guided channel-attention modulation subnetwork, to achieve this proposal. The former controls the discriminative region based on the correlation of each search feature position with all template feature positions, whereas the latter readjusts the importance of each channel based on the response value of each channel feature of the template feature and the response value of each channel of the search feature. Extensive experiments on multiple datasets have demonstrated the effectiveness of the proposed approach in this paper.