Multi-view dimensionality reduction via subspace structure agreement

X Zhao, X Wang, H Wang - Multimedia Tools and Applications, 2017 - Springer
Many state-of-the-art biometric systems make use of high-dimensional features to represent
data samples, which often contain substantial amount of intra-class variation. In this paper …

A deep neural network for audio-visual person recognition

MR Alam, M Bennamoun, R Togneri… - 2015 IEEE 7th …, 2015 - ieeexplore.ieee.org
This paper presents applications of special types of deep neural networks (DNNs) for audio-
visual biometrics. A common example is the DBN-DNN that uses the generative weights of …

Supervised multiview learning based on simultaneous learning of multiview intact and single view classifier

Q Wang, H Lv, J Yue, E Mitchell - Neural Computing and Applications, 2017 - Springer
Multiview learning problem refers to the problem of learning a classifier from multiple view
data. In this data set, each data point is presented by multiple different views. In this paper …

A framework for speaker retrieval and identification through unsupervised learning

V de Abreu Campos, DCG Pedronette - Computer Speech & Language, 2019 - Elsevier
Speaker recognition is a task of remarkable relevance, with applications in diversified
domains. Recently, mainly due to the facilities in audio-visual content acquisition, the …

Multi-view predictive latent space learning

J Yuan, K Gao, P Zhu, K Egiazarian - Pattern Recognition Letters, 2020 - Elsevier
In unsupervised circumstances, multi-view learning seeks a shared latent representation by
taking the consensus and complementary principles into account. However, most existing …

Stochastic Neighbor Embedding of Multimodal Relational Data for Image-Text Simultaneous Visualization

M Mizutani, A Okuno, G Kim, H Shimodaira - arXiv preprint arXiv …, 2020 - arxiv.org
Multimodal relational data analysis has become of increasing importance in recent years, for
exploring across different domains of data, such as images and their text tags obtained from …