Generalized Multi-view Embedding for Visual Recognition and Cross-modal Retrieval
This work addresses the challenge of integrating multiple visual views and modalities for improved recognition and retrieval, representing an incremental advancement in multi-view learning methods.
The paper tackles the problem of multi-view embedding from different visual cues and modalities by proposing a unified solution for subspace learning methods using the Rayleigh quotient, which is extensible for multiple views, supervised learning, and non-linear embeddings, and demonstrates superior results in visual object recognition and cross-modal image retrieval compared to related methods.
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.