Can Language Models Laugh at YouTube Short-form Videos?

arXiv:2310.14159v3 Announce Type: replace-cross
Abstract: As short-form funny videos on social networks are gaining popularity, it becomes demanding for AI models to understand them for better communication with humans. Unfortunately, previous video humor datasets target specific domains, such as speeches or sitcoms, and mostly focus on verbal cues. We curate a user-generated dataset of 10K multimodal funny videos from YouTube, called ExFunTube. Using a video filtering pipeline with GPT-3.5, we verify both verbal and visual elements contributing to humor. After …

abstract ai models arxiv communication cs.cl cs.cv datasets domains focus form funny generated humans humor language language models networks social social networks them type verbal video videos youtube