Recognizing Human Actions by Attributes

In this paper, the authors explore the idea of using high-level se-mantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the construction of more descriptive models for human action recognition. They propose a unified framework wherein manually specified attributes are: selected in a discriminative fashion so as to account for intra-class variability; coherently integrated with data-driven attributes to make the attribute set more descriptive. Data-driven attributes are automatically inferred from the training data using an in-formation theoretic approach.