Paper Info
Title
Audiovisual three-level fusion for continuous estimation of Russell's emotion circumplex
Abstract
Predicting human emotions is catching the attention of many research areas, which demand accurate predictions in uncontrolled scenarios. Despite this attractiveness, designed systems for emotion detection are far off being as accurate as desired. Two of the typical measurements in human emotions are described in terms of the dimensions valence and arousal, which shape the Russell's circumplex where complex emotions lie. Thus, the Affect Recognition Sub-Challenge (ASC) of the third AudioVisual Emotion and Depression Challenge, AVEC'13, is focused on estimating these two dimensions. This paper presents a three-level fusion system combining single regression results from audio and visual features, in order to maximize the mean average correlation on both dimensions. Five sets of features are extracted (three for audio and two for video), and they are merged following an iterative process. Results show how this fusion outperforms the baseline method for the challenge database.
Year
DOI
Venue
2013
10.1145/2512530.2512534
AVEC@ACM Multimedia
Keywords
Field
DocType
audiovisual three-level fusion,challenge database,affect recognition sub-challenge,accurate prediction,complex emotion,emotion circumplex,continuous estimation,three-level fusion system,depression challenge,audiovisual emotion,human emotion,dimensions valence,affective computing,support vector regression
Arousal,Computer vision,Regression,Iterative and incremental development,Computer science,Support vector machine,Fusion,Attractiveness,Correlation,Artificial intelligence,Affective computing
Conference
Citations 
PageRank 
References 
11
0.52
28
Authors
5
Name
Order
Citations
PageRank
Enrique Sánchez-Lozano1263.44
Paula Lopez-Otero26413.18
Laura Docio-Fernandez3204.00
Enrique Argones-rúa4386.69
José Luis Alba-castro514515.58