Towards Automatic Social Involvement Estimation
Z. Li (TU Delft - Pattern Recognition and Bioinformatics, TU Delft - Intelligent Systems)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Engaged in the group of Human Oriented Machine Intelligence(HOMI), my colleagues and I are working on the NEON project which focuses on social intention estimation. In particular, my job is to model and estimate social involvement, which is highly connected with the overall target. Studying social involvement will not only benefit our understanding of social interactions, but also provide crucial information for other potential applications. The work package of the research includes 1) build-up of a theoretical framework; 2) designing of the annotation framework; 3) collection of new dataset(s); 4) designing and training of the computer model.