Online Behavioral Analysis with Application to Emotion State Identification
This work addresses emotion state identification for applications requiring real-time behavioral analysis, but it appears incremental as it builds on existing discriminative modeling approaches.
The authors tackled the problem of online emotion state identification by proposing a discriminative model that extracts more discriminative characteristics from behavioral data and efficiently finds optimal projection directions, resulting in more accurate recognition results.
In this paper, we propose a novel discriminative model for online behavioral analysis with application to emotion state identification. The proposed model is able to extract more discriminative characteristics from behavioral data effectively and find the direction of optimal projection efficiently to satisfy requirements of online data analysis, leading to better utilization of the behavioral information to produce more accurate recognition results.