Object Tracking by Hierarchical Part-Whole Attention

We present in this paper that hierarchical representations of objects can provide an informative and low-noisy proxy to associate objects of interest in multi-object tracking. This is aligned with our intuition that we usually only need to compare a little region of the body of target objects to distinguish them from other objects. We build the hierarchical representation in levels of (1) target body parts, (2) the whole target body, and (3) the union area of the target and other objects of overlap. Furthermore, with the spatio-temporal attention mechanism by transformer, we can solve the tracking in a global fashion and keeps the process online. We design our method by combining the representation with the transformer and name it Hierarchical Part-Whole Attention, or HiPWA for short. The experiments on multiple datasets suggest its good effectiveness. Moreover, previous methods mostly focus on leveraging transformers to exploit long temporal context during association which requires heavy computation resources. But HiPWA focuses on a more informative representation of objects on every single frame instead. So it is more robust with the length of temporal context and more computationally economic.