Co-recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration


We introduce a new concept of ‘co-recognition’ for object-level image matching between an arbitrary image pair. Our method augments putative local regionmatches to reliable object-level correspondenceswithout any supervision or prior knowledge on common objects. It provides the number of reliable common objects and the dense correspondences between the image pair. In this paper, generative model for co-recognition is presented. For inference, we propose data-driven Monte Carlo image exploration 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 probabilitymodel. In the experiments, we demonstrate the power and utility on image retrieval and unsupervised recognition and segmentation of multiple common objects.

DOI: 10.1007/978-3-540-88693-8_11

Extracted Key Phrases

Citations per Year

58 Citations

Semantic Scholar estimates that this publication has 58 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Cho2008CorecognitionOI, title={Co-recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration}, author={Minsu Cho and Young Min Shin and Kyoung Mu Lee}, booktitle={ECCV}, year={2008} }