Abstract

As structured data, human body and text are similar in many aspects. In this paper, we make use of the analogy between hu- man body and text to build a compositional model for human detection in natural scenes. Basic concepts and mature techniques in text recog- nition are introduced into this model. A discriminative alphabet, each grapheme of which is a mid-level element representing a body part, is automatically learned from bounding box labels. Based on this alphabet, the flexible structure of human body is expressed by means of symbolic sequences, which correspond to various human poses and allow for ro- bust, efficient matching. A pose dictionary is constructed from training examples, which is used to verify hypotheses at runtime. Experiments on standard benchmarks demonstrate that the proposed algorithm achieves state-of-the-art or competitive performance.