Temporal Label Hierachical Network for Compound Emotion Recognition
This work addresses compound emotion recognition for applications like behavior analysis, but it appears incremental as it builds on existing networks and data augmentation methods.
The paper tackled compound emotion recognition, a challenge in practical applications, by proposing a temporal label hierarchical network that achieved results in the 7th ABAW competition, though no concrete numbers are provided.
The emotion recognition has attracted more attention in recent decades. Although significant progress has been made in the recognition technology of the seven basic emotions, existing methods are still hard to tackle compound emotion recognition that occurred commonly in practical application. This article introduces our achievements in the 7th Field Emotion Behavior Analysis (ABAW) competition. In the competition, we selected pre trained ResNet18 and Transformer, which have been widely validated, as the basic network framework. Considering the continuity of emotions over time, we propose a time pyramid structure network for frame level emotion prediction. Furthermore. At the same time, in order to address the lack of data in composite emotion recognition, we utilized fine-grained labels from the DFEW database to construct training data for emotion categories in competitions. Taking into account the characteristics of valence arousal of various complex emotions, we constructed a classification framework from coarse to fine in the label space.