Towards Online Impression Prediction of Oral Presentations Using Soft Coding

We have been developing impression prediction techniques for oral presentations. The contribution of this paper is two folds. First, we introduce soft code assignment for the bag-of-features (BoF) representation to improve the prediction accuracy. Second, we discuss towards online impression predict...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Second International Conference on Multimedia Big Data (BigMM) pp. 462 - 465
Main Authors Yamasaki, T., Fukushima, Y., Furuta, R., Aizawa, K.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2016
Subjects
Big data
Conferences
Multimedia communication
presentation analysis
soft coding
Online AccessGet full text
DOI10.1109/BigMM.2016.81

Cover

More Information
Summary:We have been developing impression prediction techniques for oral presentations. The contribution of this paper is two folds. First, we introduce soft code assignment for the bag-of-features (BoF) representation to improve the prediction accuracy. Second, we discuss towards online impression prediction aiming at real-time feedback to the speaker. Experimental results using over 1,600 TED presentation videos show that about 3% accuracy improvement can be achieved by the soft-coding and half amount of presentation is need to achieve comparable prediction accuracy to using the whole presentation.
DOI:10.1109/BigMM.2016.81