RATM: Recurrent Attentive Tracking Model
This work addresses object tracking in computer vision, presenting an incremental improvement with a modular framework.
The authors tackled object tracking by proposing an attention-based modular neural framework, and the resulting Recurrent Attentive Tracking Model performed well on three datasets including bouncing ball, moving digits, and KTH, generalizing to unseen sequences.
We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module controlling where to look in an image or video frame, a feature-extraction module providing a representation of what is seen, and an objective module formalizing why the model learns its attentive behavior. The attention module allows the model to focus computation on task-related information in the input. We apply the framework to several object tracking tasks and explore various design choices. We experiment with three data sets, bouncing ball, moving digits and the real-world KTH data set. The proposed Recurrent Attentive Tracking Model performs well on all three tasks and can generalize to related but previously unseen sequences from a challenging tracking data set.