Stefanos Gkikas

Dynamic fusion of multi-scale EEG signals boosts emotion recognition accuracy, revealing the nuanced interplay of temporal information in mixed emotions.

StressGAT achieves 88.62% accuracy in stress recognition by personalizing facial expression analysis, all while maintaining interpretability for clinical use.

ReFace achieves the highest reported accuracy for pain assessment from facial videos by leveraging spatial reorganization, challenging the conventional approach of treating the face as a single entity.

A unified framework for pain recognition achieves state-of-the-art results by seamlessly integrating diverse 3D data modalities without the need for separate processing architectures.

Classical feature engineering outperforms deep learning in pain localization, revealing critical insights into physiological signal interpretation.

Forget audio – this lightweight transformer predicts robot gestures from text and emotion better than GPT-4o.