Deep Tracking: Visual Tracking Using Deep Convolutional Networks
This addresses the problem of robust visual tracking for computer vision applications, but it is incremental as it builds on existing deep learning approaches.
The paper tackles visual tracking by using a discriminatively trained dual-stream deep convolutional network to extract motion and appearance features, achieving competitive performance against state-of-the-art methods on a benchmark.
In this paper, we study a discriminatively trained deep convolutional network for the task of visual tracking. Our tracker utilizes both motion and appearance features that are extracted from a pre-trained dual stream deep convolution network. We show that the features extracted from our dual-stream network can provide rich information about the target and this leads to competitive performance against state of the art tracking methods on a visual tracking benchmark.