As humans, we regularly interpret images based on the relations between image regions. For example, a person riding object X, or a plank bridging two objects. Current methods provide limited support to search for images based on such relations. We present RAID, a relation-augmented image descriptor that supports queries based on inter-region relations. The key idea of our descriptor is to capture the spatial distribution of simple point-to-region relationships to describe more complex relationships between two image regions. We evaluate the proposed descriptor by querying into a large subset of the Microsoft COCO database and successfully extract nontrivial images demonstrating complex inter-region relations, which are easily missed or erroneously classified by existing methods.
@article{arxiv.1510.01113,
title = {RAID: A Relation-Augmented Image Descriptor},
author = {Paul Guerrero and Niloy J. Mitra and Peter Wonka},
journal= {arXiv preprint arXiv:1510.01113},
year = {2015}
}
Comments
Fixed affiliation and email address of first author