Expanded Parts Model for Semantic Description of Humans in Still Images

TL;DR

The paper presents an Expanded Parts Model (EPM) that improves human attribute and action recognition in still images by learning discriminative part templates and focusing on relevant regions, achieving state-of-the-art results.

Contribution

Introduction of EPM, a discriminative, part-based model that automatically mines and learns relevant parts for human attribute and action recognition in images.

Findings

Achieves state-of-the-art results on three challenging datasets.

Effectively mines and learns discriminative parts for recognition.

Reduces background noise by sparse spatial scoring.

Abstract

We introduce an Expanded Parts Model (EPM) for recognizing human attributes (e.g. young, short hair, wearing suit) and actions (e.g. running, jumping) in still images. An EPM is a collection of part templates which are learnt discriminatively to explain specific scale-space regions in the images (in human centric coordinates). This is in contrast to current models which consist of a relatively few (i.e. a mixture of) 'average' templates. EPM uses only a subset of the parts to score an image and scores the image sparsely in space, i.e. it ignores redundant and random background in an image. To learn our model, we propose an algorithm which automatically mines parts and learns corresponding discriminative templates together with their respective locations from a large number of candidate parts. We validate our method on three recent challenging datasets of human attributes and actions. We obtain convincing qualitative and state-of-the-art quantitative results on the three datasets.