Depressive semantic awareness from vlog facial and vocal streams via spatio-temporal transformer

With the rapid growth of information transmission via the Internet, efforts have been made to reduce network load to promote efficiency. One such application is semantic computing, which can extract and process semantic communication. Social media has enabled users to share their current emotions, opinions, and life events through their mobile devices. Notably, people suffering from mental health problems are more willing to share their feelings on social networks. Therefore, it is necessary to extract semantic information from social media (vlog data) to identify abnormal emotional states to facilitate early identification and intervention. Most studies do not consider spatio-temporal information when fusing multimodal information to identify abnormal emotional states such as depression. To solve this problem, this paper proposes a spatio-temporal squeeze transformer method for the extraction of semantic features of depression. First, a module with spatio-temporal data is embedded into the transformer encoder, which is utilized to obtain a representation of spatio-temporal features. Second, a classifier with a voting mechanism is designed to encourage the model to classify depression and non-depression effectively. Experiments are conducted on the D-Vlog dataset. The results show that the method is effective, and the accuracy rate can reach 70.70%. This work provides scaffolding for future work in the detection of affect recognition in semantic communication based on social media vlog data.