Hetero-Manifold Regularisation for Cross-Modal Hashing

Ling Shao, Fellow of Ieee/iapr, Feng Zheng, Yi Tang, Ling Shao

Abstract

Recently, cross-modal search has attracted considerable attention but remains a very challenging task because of the integration complexity and heterogeneity of the multi-modal data. To address both challenges, in this paper, we propose a novel method termed hetero-manifold regularisation (HMR) to supervise the learning of hash functions for efficient cross-modal search. A hetero-manifold integrates multiple sub-manifolds defined by homogeneous data with the help of cross-modal supervision information. Taking advantages of the hetero-manifold, the similarity between each pair of heterogeneous data could be naturally measured by three order random walks on this hetero-manifold. Furthermore, a novel cumulative distance inequality defined on the hetero-manifold is introduced to avoid the computational difficulty induced by the discreteness of hash codes. By using the inequality, cross-modal hashing is transformed into a problem of hetero-manifold regularised support vector learning. Therefore, the performance of cross-modal search can be significantly improved by seamlessly combining the integrated information of the hetero-manifold and the strong generalisation of the support vector machine. Comprehensive experiments show that the proposed HMR achieve advantageous results over the state-of-the-art methods in several challenging cross-modal tasks.
BibTeX
@article{ieeeiapr2018hetero,
  author = {Ling Shao, Fellow of IEEE/IAPR and Feng Zheng and Yi Tang and Ling Shao},
  title = {{Hetero-Manifold Regularisation for Cross-Modal Hashing}},
  journal = {IEEE TPAMI},
  year = {2018},
  doi = {10.1109/tpami.2016.2645565},
}
Figure