Abstract

This paper presents a new ob ject representation, Active Mask Hierarchies (AMH), for ob ject detection. In this representation, an ob ject is described using a mixture of hierarchical trees where the nodes represent the ob ject and its parts in pyramid form. To account for shape variations at a range of scales, a dictionary of masks with varied shape patterns are attached to the nodes at different layers. The shape masks are “active” in that they enable parts to move with different dis- placements. The masks in this active hierarchy are associated with his- tograms of words (HOWs) and oriented gradients (HOGs) to enable rich appearance representation of both structured (eg, cat face) and textured (eg, cat body) image regions. Learning the hierarchical model is a latent SVM problem which can be solved by the incremental concave-convex procedure (iCCCP). The resulting system is comparable with the state- of-the-art methods when evaluated on the challenging public PASCAL 2007 and 2009 datasets.