Behavior Analysis in the Wild
Behavior analysis in the wild focuses on automatically recognizing human emotions and affective states from unconstrained real-world videos and audio. Current research heavily utilizes deep learning, particularly employing transformer networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs) like LSTMs, often in multi-task and multi-modal frameworks that integrate visual, audio, and even textual data. These advancements aim to improve the accuracy and robustness of emotion recognition systems, with significant implications for applications such as human-computer interaction, mental health monitoring, and personalized experiences.
Papers
An Attention-based Method for Action Unit Detection at the 3rd ABAW Competition
Duy Le Hoai, Eunchae Lim, Eunbin Choi, Sieun Kim, Sudarshan Pant, Guee-Sang Lee, Soo-Huyng Kim, Hyung-Jeong Yang
Transformer-based Multimodal Information Fusion for Facial Expression Analysis
Wei Zhang, Feng Qiu, Suzhen Wang, Hao Zeng, Zhimeng Zhang, Rudong An, Bowen Ma, Yu Ding