Paper Info
Title
Combining feature-level and decision-level fusion in a hierarchical classifier for emotion recognition in the wild.
Abstract
Emotion recognition in the wild is a very challenging task. In this paper, we investigate a variety of different multimodal features (acoustic and visual) from video clips to evaluate their discriminative abilities in human emotion analysis. For each clip, we extract MSDF BoW, LBP-TOP, PHOG, LPQ-TOP and Audio features. We train different classifiers for every type of feature on the AFEW dataset from the ICMI 2014 EmotiW Challenge, and we propose a novel hierarchical classification framework, which combines the feature-level and decision-level fusion strategy for all of the extracted multimodal features. The final achievement we gain on the AFEW test set is 47.17 %, which is considerably better than the best baseline recognition rate of 33.7 %. Among all of the teams participating in the ICMI 2014 EmotiW challenge, our recognition performance won the first runner-up award. Furthermore, we test our method on FERA and CK datasets, the experimental results also show good performance.
Year
DOI
Venue
2016
https://doi.org/10.1007/s12193-015-0203-6
J. Multimodal User Interfaces
Keywords
Field
DocType
Emotion recognition,Multimodal features,Feature-level fusion,Decision-level fusion,Multiple kernel learning,Hierarchical classifier
Decision level,Pattern recognition,Computer science,Emotion recognition,Multiple kernel learning,Speech recognition,Artificial intelligence,Hierarchical classifier,Discriminative model,Test set
Journal
Volume
Issue
ISSN
10
2
1783-7677
Citations 
PageRank 
References 
7
0.45
32
Authors
8
Name
Order
Citations
PageRank
Bo Sun110421.35
Liandong Li2775.02
Xuewen Wu3412.16
Tian Zuo4341.39
Ying Chen511516.65
Guoyan Zhou6512.27
Jun He77111.24
Xiaoming Zhu870.79