The Community for Technology Leaders
Green Image
ISSN: 0162-8828
Jonathan Masci , Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA), Manno
Michael M. Bronstein , Università della Svizzera Italiana, Lugano
Alexander M. Bronstein , Tel Aviv University, Tel Aviv and Intel Semiconductor, Israel
Jürgen Schmidhuber , Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA), Manno
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.
multimodal data, Computer vision, Machine learning, similarity-sensitive hashing, neural networks

J. Masci, M. M. Bronstein, A. M. Bronstein and J. Schmidhuber, "Multimodal Similarity-Preserving Hashing," in IEEE Transactions on Pattern Analysis & Machine Intelligence.
294 ms
(Ver 3.3 (11022016))