See a list of publications below or visit the Photonics academic staff page and click on a particular member of staff to access their personal web page, which includes a list of their own publications.
@article{Kumar:2021:10.1007/s00371-019-01788-2,
author = {Kumar, S and Bhuyan, MK and Iwahori, Y},
doi = {10.1007/s00371-019-01788-2},
journal = {Visual Computer},
pages = {143--159},
title = {Multi-level uncorrelated discriminative shared Gaussian process for multi-view facial expression recognition},
url = {http://dx.doi.org/10.1007/s00371-019-01788-2},
volume = {37},
year = {2021}
}
TY - JOUR
AB - In multi-view facial expression recognition, discriminative shared Gaussian process latent variable model (DS-GPLVM) gives better performance than that of linear and nonlinear multi-view learning-based methods. However, Laplacian-based prior used in DS-GPLVM only captures topological structure of data space without considering the inter-class separability of the data, and hence the obtained latent space is suboptimal. So, we propose a multi-level uncorrelated DS-GPLVM (ML-UDSGPLVM) model which searches a common uncorrelated discriminative latent space learned from multiple observable spaces. A novel prior is proposed, which not only depends on the topological structure of the intra-class data, but also on the local-between-class-scatter-matrix of the data onto the latent manifold. The proposed approach employs an hierarchical framework, in which, expressions are first divided into three sub-categories. Subsequently, each of the sub-categories are further classified to identify the constituent basic expressions. Experimental results show that the proposed method outperforms state-of-the-art methods in many instances.
AU - Kumar,S
AU - Bhuyan,MK
AU - Iwahori,Y
DO - 10.1007/s00371-019-01788-2
EP - 159
PY - 2021///
SN - 0178-2789
SP - 143
TI - Multi-level uncorrelated discriminative shared Gaussian process for multi-view facial expression recognition
T2 - Visual Computer
UR - http://dx.doi.org/10.1007/s00371-019-01788-2
VL - 37
ER -