Group Level Emotion

Group-level emotion recognition (GER) aims to identify the overall emotional state of a group of people, a complex task due to the diversity and dynamic interplay of individual emotions. Current research heavily utilizes deep learning, employing architectures like convolutional neural networks (CNNs), vision transformers (ViTs), and recurrent neural networks (RNNs), often in multimodal frameworks combining visual and auditory data, to analyze group interactions and extract relevant features. This field is significant for its potential applications in areas such as social robotics, human-computer interaction, and mental health analysis, with recent work focusing on improving robustness to noise and occlusion, and developing privacy-preserving methods.