Group-level emotion recognition using transfer learning from face identification
Open Access
- 3 November 2017
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 544-548
Abstract
In this paper, we describe our algorithmic approach, which was used for submissions in the fifth Emotion Recognition in the Wild (EmotiW 2017) group-level emotion recognition sub-challenge. We extracted feature vectors of detected faces using the Convolutional Neural Network trained for face identification task, rather than traditional pre-training on emotion recognition problems. In the final pipeline an ensemble of Random Forest classifiers was learned to predict emotion score using available training set. In case when the faces have not been detected, one member of our ensemble extracts features from the whole image. During our experimental study, the proposed approach showed the lowest error rate when compared to other explored techniques. In particular, we achieved 75.4% accuracy on the validation data, which is 20% higher than the handcrafted feature-based baseline. The source code using Keras framework is publicly available.Comment: 5 pages, 3 figures, accepted for publication at ICMI17 (EmotiW Grand ChallengeKeywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Happiness level prediction with sequential inputs via multiple regressions2016
- LSTM for dynamic emotion and group emotion recognition in the wild2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Challenges in representation learning: A report on three machine learning contestsNeural Networks, 2015
- Automatic Group Happiness Intensity AnalysisIEEE Transactions on Affective Computing, 2015
- Riesz-based Volume Local Binary Pattern and A Novel Group Expression Model for Group Happiness Intensity Analysis2015
- Deep Face Recognition2015
- Automatic Analysis of Facial Affect: A Survey of Registration, Representation, and RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- One millisecond face alignment with an ensemble of regression trees2014
- Histograms of Oriented Gradients for Human Detection2005