Output-associative RVM regression for dimensional and continuous emotion prediction


Share/Save/Bookmark

Nicolaou, Mihalis A. and Gunes, Hatice and Pantic, Maja (2011) Output-associative RVM regression for dimensional and continuous emotion prediction. In: IEEE International Conference on Automatic Face & Gesture Recognition and Workshops, FG 2011, 21-25 March 2011, Santa Barbara, CA (pp. pp. 16-23).

[img] PDF
Restricted to UT campus only
: Request a copy
713kB
Abstract:Many problems in machine learning and computer vision consist of predicting multi-dimensional output vectors given a specific set of input features. In many of these problems, there exist inherent temporal and spacial dependencies between the output vectors, as well as repeating output patterns and input-output associations, that can provide more robust and accurate predictors when modelled properly. With this intrinsic motivation, we propose a novel Output-Associative Relevance Vector Machine (OA-RVM) regression framework that augments the traditional RVM regression by being able to learn non-linear input and output dependencies. Instead of depending solely on the input patterns, OA-RVM models output structure and covariances within a predefined temporal window, thus capturing past, current and future context. As a result, output patterns manifested in the training data are captured within a formal probabilistic framework, and subsequently used during inference. As a proof of concept, we target the highly challenging problem of dimensional and continuous prediction of emotions from naturalistic facial expressions. We demonstrate the advantages of the proposed OA-RVM regression by performing both subject-dependent and subject-independent experiments using the SAL database. The experimental results show that OA-RVM regression outperforms the traditional RVM and SVM regression approaches in prediction accuracy,generating more robust and accurate models.
Item Type:Conference or Workshop Item
Copyright:© 2011 IEEE
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/79503
Official URL:http://dx.doi.org/10.1109/FG.2011.5771396
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page