Abstract

We introduce a new concept of ‘co-recognition’ for ob ject-level image matching between an arbitrary image pair. Our method augments putative local region matches to reliable ob ject-level correspondences with- out any supervision or prior knowledge on common ob jects. It provides the number of reliable common ob jects and the dense correspondences be- tween the image pair. In this paper, generative model for co-recognition is presented. For inference, we propose data-driven Monte Carlo image ex- ploration which clusters and propagates local region matches by Markov chain dynamics. The global optimum is achieved by a guiding force of our data-driven sampling and posterior probability model. In the experiments, we demonstrate the power and utility on image retrieval and unsupervised recognition and segmentation of multiple common ob jects.