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.
22papers
Papers
March 13, 2025
July 18, 2024
March 18, 2024
Unimodal Multi-Task Fusion for Emotional Mimicry Intensity Prediction
HSEmotion Team at the 6th ABAW Competition: Facial Expressions, Valence-Arousal and Emotion Intensity Prediction
Zero-shot Compound Expression Recognition with Visual Language Model at the 6th ABAW Challenge
Boosting Continuous Emotion Recognition with Self-Pretraining using Masked Autoencoders, Temporal Convolutional Networks, and Transformers
March 19, 2023
March 18, 2023
March 17, 2023
March 16, 2023
March 15, 2023