Saliency-guided Emotion Modeling: Predicting Viewer Reactions from Video Stimuli
This work addresses emotion prediction for content creators and HCI applications by offering a computationally efficient alternative, though it is incremental as it builds on existing saliency and emotion analysis methods.
The study tackled the problem of predicting viewer emotions from videos by incorporating visual saliency features, revealing that multiple salient regions correlate with high-valence, low-arousal emotions, while a single dominant region correlates with low-valence, high-arousal responses.
Understanding the emotional impact of videos is crucial for applications in content creation, advertising, and Human-Computer Interaction (HCI). Traditional affective computing methods rely on self-reported emotions, facial expression analysis, and biosensing data, yet they often overlook the role of visual saliency -- the naturally attention-grabbing regions within a video. In this study, we utilize deep learning to introduce a novel saliency-based approach to emotion prediction by extracting two key features: saliency area and number of salient regions. Using the HD2S saliency model and OpenFace facial action unit analysis, we examine the relationship between video saliency and viewer emotions. Our findings reveal three key insights: (1) Videos with multiple salient regions tend to elicit high-valence, low-arousal emotions, (2) Videos with a single dominant salient region are more likely to induce low-valence, high-arousal responses, and (3) Self-reported emotions often misalign with facial expression-based emotion detection, suggesting limitations in subjective reporting. By leveraging saliency-driven insights, this work provides a computationally efficient and interpretable alternative for emotion modeling, with implications for content creation, personalized media experiences, and affective computing research.