Infinite Latent Conditional Random Fields for Modeling Environments through Humans

Abstract

Humans cast a substantial influence on their environments by interacting with it. Therefore, even though an environment may physically contain only objects, it cannot be modeled well without considering humans. In this paper, we model environments not only through objects, but also through latent human poses and human-object interactions. However, the number of potential human poses is large and unknown, and the human-object interactions vary not only in type but also in which human pose relates to each object. In order to handle such properties, we present Infinite Latent Conditional Random Fields (ILCRFs) that model a scene as a mixture of CRFs generated from Dirichlet processes. Each CRF represents one possible explanation of the scene. In addition to visible object nodes and edges, it generatively models the distribution of different CRF structures over the latent human nodes and corresponding edges. We apply the model to the challenging application of robotic scene arrangement. In extensive experiments, we show that our model significantly outperforms the state-of-the-art results. We further use our algorithm on a robot for placing objects in a new scene.