Command Palette
Search for a command to run...
Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition
Hengshun Zhou; Debin Meng; Yuanyuan Zhang; Xiaojiang Peng; Jun Du; Kai Wang; Yu Qiao
Abstract
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.
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| facial-expression-recognition-on-acted-facial | LResNet50E-IR (5 models with augmentation) | Accuracy(on validation set): 65.5% |
| facial-expression-recognition-on-acted-facial | ResNet50 | Accuracy(on validation set): 65.5% |
| facial-expression-recognition-on-acted-facial | LResNet50E-IR (1 model) | Accuracy(on validation set): 61.1% |
| facial-expression-recognition-on-acted-facial | LResNet50E-IR (1 model with augmentation) | Accuracy(on validation set): 63.7% |
| facial-expression-recognition-on-affectnet | LResNet50E-IR | Accuracy (8 emotion): 53.925 |
| facial-expression-recognition-on-fer-1 | LResNet50E-IR | Accuracy: 89.257 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.