Mohammad Saeed Ehsani

Maysam Behmanesh, Peyman Adibi, Mohammad Saeed Ehsani et al.

Multimodal data provide complementary information of a natural phenomenon by integrating data from various domains with very different statistical properties. Capturing the intra-modality and cross-modality information of multimodal data is the essential capability of multimodal learning methods. The geometry-aware data analysis approaches provide these capabilities by implicitly representing data in various modalities based on their geometric underlying structures. Also, in many applications, data are explicitly defined on an intrinsic geometric structure. Generalizing deep learning methods to the non-Euclidean domains is an emerging research field, which has recently been investigated in many studies. Most of those popular methods are developed for unimodal data. In this paper, a multimodal multi-scaled graph wavelet convolutional network (M-GWCN) is proposed as an end-to-end network. M-GWCN simultaneously finds intra-modality representation by applying the multiscale graph wavelet transform to provide helpful localization properties in the graph domain of each modality, and cross-modality representation by learning permutations that encode correlations among various modalities. M-GWCN is not limited to either the homogeneous modalities with the same number of data, or any prior knowledge indicating correspondences between modalities. Several semi-supervised node classification experiments have been conducted on three popular unimodal explicit graph-based datasets and five multimodal implicit ones. The experimental results indicate the superiority and effectiveness of the proposed methods compared with both spectral graph domain convolutional neural networks and state-of-the-art multimodal methods.

Maysam Behmanesh, Peyman Adibi, Jocelyn Chanussot et al.

Multimodal manifold modeling methods extend the spectral geometry-aware data analysis to learning from several related and complementary modalities. Most of these methods work based on two major assumptions: 1) there are the same number of homogeneous data samples in each modality, and 2) at least partial correspondences between modalities are given in advance as prior knowledge. This work proposes two new multimodal modeling methods. The first method establishes a general analyzing framework to deal with the multimodal information problem for heterogeneous data without any specific prior knowledge. For this purpose, first, we identify the localities of each manifold by extracting local descriptors via spectral graph wavelet signatures (SGWS). Then, we propose a manifold regularization framework based on the functional mapping between SGWS descriptors (FMBSD) for finding the pointwise correspondences. The second method is a manifold regularized multimodal classification based on pointwise correspondences (M$^2$CPC) used for the problem of multiclass classification of multimodal heterogeneous, which the correspondences between modalities are determined based on the FMBSD method. The experimental results of evaluating the FMBSD method on three common cross-modal retrieval datasets and evaluating the (M$^2$CPC) method on three benchmark multimodal multiclass classification datasets indicate their effectiveness and superiority over state-of-the-art methods.