Generalized Multi-view Embedding for Visual Recognition and Cross-modal Retrieval

Abstract

In this paper, the problem of multi-view embed-ding from different visual cues and modalities is considered. We propose a unified solution for subspace learning methods using the Rayleigh quotient, which is extensible for multiple<br/>views, supervised learning, and non-linear embeddings. Numerous methods including Canonical Correlation Analysis, Partial Least Square regression and Linear Discriminant Analysis are studied using specific intrinsic and penalty graphs within the same framework. Non-linear extensions based on kernels and<br/>(deep) neural networks are derived, achieving better performance than the linear ones. Moreover, a novel Multi-view Modular Discriminant Analysis (MvMDA) is proposed by taking the view difference into consideration. We demonstrate the effectiveness of the proposed multi-view embedding methods on visual object<br/>recognition and cross-modal image retrieval, and obtain superior results in both applications compared to related methods.