Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition

27 Dec 2020  ·  Hengshun Zhou, Debin Meng, Yuanyuan Zhang, Xiaojiang Peng, Jun Du, Kai Wang, Yu Qiao ·

The audio-video based emotion recognition aims to classify a given video into basic emotions. In this paper, we describe our approaches in EmotiW 2019, which mainly explores emotion features and feature fusion strategies for audio and visual modality. For emotion features, we explore audio feature with both speech-spectrogram and Log Mel-spectrogram and evaluate several facial features with different CNN models and different emotion pretrained strategies. For fusion strategies, we explore intra-modal and cross-modal fusion methods, such as designing attention mechanisms to highlights important emotion feature, exploring feature concatenation and factorized bilinear pooling (FBP) for cross-modal feature fusion. With careful evaluation, we obtain 65.5% on the AFEW validation set and 62.48% on the test set and rank third in the challenge.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Facial Expression Recognition (FER) Acted Facial Expressions In The Wild (AFEW) ResNet50 Accuracy(on validation set) 65.5% # 1
Facial Expression Recognition (FER) Acted Facial Expressions In The Wild (AFEW) LResNet50E-IR (1 model with augmentation) Accuracy(on validation set) 63.7% # 4
Facial Expression Recognition (FER) Acted Facial Expressions In The Wild (AFEW) LResNet50E-IR (5 models with augmentation) Accuracy(on validation set) 65.5% # 1
Facial Expression Recognition (FER) Acted Facial Expressions In The Wild (AFEW) LResNet50E-IR (1 model) Accuracy(on validation set) 61.1% # 5
Facial Expression Recognition (FER) AffectNet LResNet50E-IR Accuracy (8 emotion) 53.925 # 27
Facial Expression Recognition (FER) FER+ LResNet50E-IR Accuracy 89.257 # 8

Methods


No methods listed for this paper. Add relevant methods here