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

TL;DR

This paper introduces a unified multi-view embedding framework that integrates various subspace learning methods, extends to non-linear models, and improves visual recognition and cross-modal retrieval performance.

Contribution

It presents a generalized Rayleigh quotient-based approach for multi-view embedding, including a novel Multi-view Modular Discriminant Analysis (MvMDA).

Findings

Outperforms existing methods in visual object recognition.

Achieves superior results in cross-modal image retrieval.

Demonstrates effectiveness of non-linear extensions.

Abstract

In this paper, the problem of multi-view embedding 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 views, supervised learning, and non-linear embeddings. Numerous methods including Canonical Correlation Analysis, Partial Least Sqaure regression and Linear Discriminant Analysis are studied using specific intrinsic and penalty graphs within the same framework. Non-linear extensions based on kernels and (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 recognition and cross-modal image retrieval, and obtain superior results in both applications compared to related methods.