English

FunQA: Towards Surprising Video Comprehension

Computer Vision and Pattern Recognition 2024-03-25 v2 Artificial Intelligence Computation and Language Multimedia

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 focus on less surprising contexts, e.g., cooking or instructional videos, FunQA covers three previously unexplored types of surprising videos: 1) HumorQA, 2) CreativeQA, and 3) MagicQA. For each subset, we establish rigorous QA tasks designed to assess the model's capability in counter-intuitive timestamp localization, detailed video description, and reasoning around counter-intuitiveness. We also pose higher-level tasks, such as attributing a fitting and vivid title to the video and scoring the video creativity. In total, the FunQA benchmark consists of 312K free-text QA pairs derived from 4.3K video clips, spanning a total of 24 video hours. Moreover, we propose FunMentor, an agent designed for Vision-Language Models (VLMs) that uses multi-turn dialogues to enhance models' understanding of counter-intuitiveness. Extensive experiments with existing VLMs demonstrate the effectiveness of FunMentor and reveal significant performance gaps for the FunQA videos across spatial-temporal reasoning, visual-centered reasoning, and free-text generation.

Keywords

Cite

@article{arxiv.2306.14899,
  title  = {FunQA: Towards Surprising Video Comprehension},
  author = {Binzhu Xie and Sicheng Zhang and Zitang Zhou and Bo Li and Yuanhan Zhang and Jack Hessel and Jingkang Yang and Ziwei Liu},
  journal= {arXiv preprint arXiv:2306.14899},
  year   = {2024}
}

Comments

Project Page: https://funqa-benchmark.github.io/ Codebase: https://github.com/Jingkang50/FunQA

R2 v1 2026-06-28T11:14:51.542Z