Abstract
This paper focuses on audio-visual (using facial expression, shoulder and audio cues) classification of spontaneous affect, utilising generative models for classification (i) in terms of Maximum Likelihood Classification with the assumption that the generative model structure in the classifier is correct, and (ii) Likelihood Space Classification with the assumption that the generative model structure in the classifier may be incorrect, and therefore, the classification performance can be improved by projecting the results of generative classifiers onto likelihood space, and then using discriminative classifiers. Experiments are conducted by utilising Hidden Markov Models for single cue classification, and 2 and 3-chain coupled Hidden Markov Models for fusing multiple cues and modalities. For discriminative classification, we utilise Support Vector Machines. Results show that Likelihood Space Classification improves the performance (91.76%) of Maximum Likelihood Classification (79.1%). Thereafter, we introduce the concept of fusion in the likelihood space, which is shown to outperform the typically used model-level fusion, attaining a classification accuracy of 94.01% and further improving all previous results.
Original language | Undefined |
---|---|
Title of host publication | 20th International Conference on Pattern Recognition, ICPR 2010 |
Place of Publication | USA |
Publisher | IEEE Computer Society |
Pages | 3695-3699 |
Number of pages | 5 |
ISBN (Print) | 978-0-7695-4109-9 |
DOIs | |
Publication status | Published - 26 Aug 2010 |
Event | 20th International Conference on Pattern Recognition 2010 - Istanbul Convention & Exhibition Centre, Istanbul, Turkey Duration: 23 Aug 2010 → 26 Aug 2010 Conference number: 20 https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=16097 |
Publication series
Name | |
---|---|
Publisher | IEEE Computer Society |
Conference
Conference | 20th International Conference on Pattern Recognition 2010 |
---|---|
Abbreviated title | ICPR 2010 |
Country/Territory | Turkey |
City | Istanbul |
Period | 23/08/10 → 26/08/10 |
Internet address |
Keywords
- METIS-276353
- IR-75937
- EWI-19536
- HMI-MI: MULTIMODAL INTERACTIONS
- EC Grant Agreement nr.: FP7/211486