Affect Estimation in 3D Space Using Multi-Task Active Learning for Regression

TL;DR

This paper introduces multi-task active learning methods for affect estimation in 3D space, effectively reducing labeling effort while improving estimation accuracy in affective computing.

Contribution

It proposes novel multi-task active learning approaches that consider valence, arousal, and dominance simultaneously for more efficient affective data labeling.

Findings

Outperforms random selection in affect estimation accuracy

Reduces number of labeled samples needed for effective training

Demonstrates effectiveness on the VAM corpus

Abstract

Acquisition of labeled training samples for affective computing is usually costly and time-consuming, as affects are intrinsically subjective, subtle and uncertain, and hence multiple human assessors are needed to evaluate each affective sample. Particularly, for affect estimation in the 3D space of valence, arousal and dominance, each assessor has to perform the evaluations in three dimensions, which makes the labeling problem even more challenging. Many sophisticated machine learning approaches have been proposed to reduce the data labeling requirement in various other domains, but so far few have considered affective computing. This paper proposes two multi-task active learning for regression approaches, which select the most beneficial samples to label, by considering the three affect primitives simultaneously. Experimental results on the VAM corpus demonstrated that our optimal sample selection approaches can result in better estimation performance than random selection and several traditional single-task active learning approaches. Thus, they can help alleviate the data labeling problem in affective computing, i.e., better estimation performance can be obtained from fewer labeling queries.