Chi-Chun Lee, Athanasios Katsamanis, Matthew P. Black, Brian Baucom, Panayiotis Georgiou, and Shrikanth S. Narayanan. Affective State Recognition in Married Couples' Interactions Using PCA-based Vocal Entrainment Measures with Multiple Instance Learning. In Proceedings of Affective Computing and Intelligent Interaction (ACII), Lecture Notes in Computer Science, oct 2011.
Recently there has been an increase in efforts in BehavioralSignal Processing (BSP), that aims to bring quantitative analysis usingsignal processing techniques in the domain of observational coding.Currently observational coding in fields such as psychology is based onsubjective expert coding of abstract human interaction dynamics. In thiswork, we use a Multiple Instance Learning (MIL) framework, a saliencybasedprediction model, with a signal-driven vocal entrainment measureas the feature to predict the affective state of a spouse in problem solvinginteractions. We generate 18 MIL classifiers to capture the variablelengthsaliency of vocal entrainment, and a cross-validation scheme withmaximum accuracy and mutual information as the metric to select thebest performing classifier for each testing couple. This method obtains arecognition accuracy of 53.93%, a 2.14% (4.13% relative) improvementover baseline model using Support Vector Machine. Furthermore, thisMIL-based framework has potential for identifying meaningful regions ofinterest for further detailed analysis of married couples interactions.
@inproceedings{Lee2011AffectiveStateRecognitionin,
abstract = {Recently there has been an increase in efforts in Behavioral
Signal Processing (BSP), that aims to bring quantitative analysis using
signal processing techniques in the domain of observational coding.
Currently observational coding in fields such as psychology is based on
subjective expert coding of abstract human interaction dynamics. In this
work, we use a Multiple Instance Learning (MIL) framework, a saliencybased
prediction model, with a signal-driven vocal entrainment measure
as the feature to predict the affective state of a spouse in problem solving
interactions. We generate 18 MIL classifiers to capture the variablelength
saliency of vocal entrainment, and a cross-validation scheme with
maximum accuracy and mutual information as the metric to select the
best performing classifier for each testing couple. This method obtains a
recognition accuracy of 53.93\%, a 2.14\% (4.13\% relative) improvement
over baseline model using Support Vector Machine. Furthermore, this
MIL-based framework has potential for identifying meaningful regions of
interest for further detailed analysis of married couples interactions.},
author = {Lee, Chi-Chun and Katsamanis, Athanasios and Black, Matthew P. and Baucom, Brian and Georgiou, Panayiotis and Narayanan, Shrikanth S.},
bib2html_rescat = {},
booktitle = {Proceedings of Affective Computing and Intelligent Interaction (ACII), Lecture Notes in Computer Science},
doi = {10.1007/978-3-642-24571-8_4},
link = {http://sail.usc.edu/publications/files/69750031.pdf},
location = {Memphis, TN},
month = {oct},
title = {Affective State Recognition in Married Couples' Interactions Using PCA-based Vocal Entrainment Measures with Multiple Instance Learning},
year = {2011}
}
Generated by bib2html.pl (written by Patrick Riley ) on Fri Mar 22, 2024 09:15:41