SANet: Structure-Aware Network for Visual Tracking
This addresses the issue of robust visual tracking for applications like surveillance or robotics, but it is incremental as it combines existing CNN and RNN techniques.
The paper tackles the problem of visual trackers being sensitive to similar distractors by using self-structure information of objects, and the result is that the proposed SANet algorithm outperforms other methods on benchmarks like OTB100, TC-128, and VOT2015.
Convolutional neural network (CNN) has drawn increasing interest in visual tracking owing to its powerfulness in feature extraction. Most existing CNN-based trackers treat tracking as a classification problem. However, these trackers are sensitive to similar distractors because their CNN models mainly focus on inter-class classification. To address this problem, we use self-structure information of object to distinguish it from distractors. Specifically, we utilize recurrent neural network (RNN) to model object structure, and incorporate it into CNN to improve its robustness to similar distractors. Considering that convolutional layers in different levels characterize the object from different perspectives, we use multiple RNNs to model object structure in different levels respectively. Extensive experiments on three benchmarks, OTB100, TC-128 and VOT2015, show that the proposed algorithm outperforms other methods. Code is released at http://www.dabi.temple.edu/~hbling/code/SANet/SANet.html.