Multimodal similarity-preserving hashing
Computer Vision and Pattern Recognition
2012-07-09 v1 Neural and Evolutionary Computing
Abstract
We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- and inter-modality similarity learning. Unlike existing cross-modality similarity learning approaches, our hashing functions are not limited to binarized linear projections and can assume arbitrarily complex forms. We show experimentally that our method significantly outperforms state-of-the-art hashing approaches on multimedia retrieval tasks.
Cite
@article{arxiv.1207.1522,
title = {Multimodal similarity-preserving hashing},
author = {Jonathan Masci and Michael M. Bronstein and Alexander A. Bronstein and Jürgen Schmidhuber},
journal= {arXiv preprint arXiv:1207.1522},
year = {2012}
}