Get Started
Home
Topics
Search
Library
Research questionHow can real-time emotion recognition in VR handle upper-face cues occluded by head-mounted displays?Head-mounted displays obscure upper-face expressions, leaving visual emotion-recognition systems with incomplete evidence for distinguishing affective states. This is especially difficult when recognition must operate during VR interaction.
Computer Vision
Image & Video Processing
Machine Learning
Multimodal Models
Latest papersRecent research connected to this question, newest first.Occlusion-Robust Multimodal Emotion Recognition in VR via Fusion of Facial Images and EMGThe study uses synchronized lower-face video and seven-channel upper-face EMG from 20 participants. It reports subject-independent classification across six basic emotions plus neutral, with late fusion reaching 51% macro-F1 versus 41% for video-only and 43% for EMG-only baselines. The dataset is available upon request under an ethical-use agreement.research paper · Sep 3, 2026
Related questions
How can speech and facial cues be combined for emotion recognition when timing and class balance vary?How can affective AI be evaluated using long-term, naturalistic, passively sensed workplace data?How can ViT-based video facial-expression recognition detect subtle, localized temporal changes that global attention overlooks?How can robots recognize social gestures in real time despite occlusion, viewpoint changes, and noisy keypoints?