SOURCE-LINKED INTELLIGENCE

Video2Reaction: Training Foundation Video Models to Predict Audience Reaction

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

We introduce Video2Reaction, a multimodal dataset that maps short movie segments to the induced emotional reactions of viewers in the wild, as expressed through social media comments. Video2Reaction captures the natural diversity of emotional responses by aggregating reactions from online comments at scale, modeling labels as distributions over categorical emotions to better reflect the subjective and ambiguous nature of emotional perception. We benchmark two vision-language models (VLMs) finetuned with LoRA, showing that VLMs learn effectively from Video2Reaction and outperform specialized ba

Read original source ↗ Open in workspace

recordType

paper

region

Global