SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models
This work addresses a new problem in social intelligence for AI systems, focusing on laughter understanding in videos, but it is incremental as it builds on existing multimodal and language model techniques.
The authors tackled the challenge of understanding why people laugh in videos by introducing the Video Laugh Reasoning task and the SMILE dataset, which includes video clips and language descriptions, and showed that a baseline using large language models with textual video representations can generate plausible explanations.
Despite the recent advances of the artificial intelligence, building social intelligence remains a challenge. Among social signals, laughter is one of the distinctive expressions that occurs during social interactions between humans. In this work, we tackle a new challenge for machines to understand the rationale behind laughter in video, Video Laugh Reasoning. We introduce this new task to explain why people laugh in a particular video and a dataset for this task. Our proposed dataset, SMILE, comprises video clips and language descriptions of why people laugh. We propose a baseline by leveraging the reasoning capacity of large language models (LLMs) with textual video representation. Experiments show that our baseline can generate plausible explanations for laughter. We further investigate the scalability of our baseline by probing other video understanding tasks and in-the-wild videos. We release our dataset, code, and model checkpoints on https://github.com/postech-ami/SMILE-Dataset.