FunQA: Towards Surprising Video Comprehension

arXiv:2306.14899v2 Announce Type: replace
Abstract: Surprising videos, such as funny clips, creative performances, or visual illusions, attract significant attention. Enjoyment of these videos is not simply a response to visual stimuli; rather, it hinges on the human capacity to understand (and appreciate) commonsense violations depicted in these videos. We introduce FunQA, a challenging video question-answering (QA) dataset specifically designed to evaluate and enhance the depth of video reasoning based on counter-intuitive and fun videos. Unlike most video QA benchmarks which …

abstract arxiv attention capacity creative cs.ai cs.cl cs.cv cs.mm funny human performances question type video videos visual