Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild
This work addresses a domain-specific problem for improving facial expression analysis in real-world video applications, with incremental contributions.
The paper tackles the challenge of dynamic facial expression recognition (DFER) in videos, where varying expression intensities cause large intra-class differences, by proposing an intensity-aware loss and global convolution-attention block, resulting in state-of-the-art performance on DFEW and FERV39k datasets.
Compared with the image-based static facial expression recognition (SFER) task, the dynamic facial expression recognition (DFER) task based on video sequences is closer to the natural expression recognition scene. However, DFER is often more challenging. One of the main reasons is that video sequences often contain frames with different expression intensities, especially for the facial expressions in the real-world scenarios, while the images in SFER frequently present uniform and high expression intensities. However, if the expressions with different intensities are treated equally, the features learned by the networks will have large intra-class and small inter-class differences, which is harmful to DFER. To tackle this problem, we propose the global convolution-attention block (GCA) to rescale the channels of the feature maps. In addition, we introduce the intensity-aware loss (IAL) in the training process to help the network distinguish the samples with relatively low expression intensities. Experiments on two in-the-wild dynamic facial expression datasets (i.e., DFEW and FERV39k) indicate that our method outperforms the state-of-the-art DFER approaches. The source code will be made publicly available.