MovieCORE：电影中的认知推理
MovieCORE: COgnitive REasoning in Movies
AI总结：
本文提出MovieCORE数据集，通过多LLM智能体生成深层认知问答，并引入ACE模块将VQA模型推理能力提升25%，推进AI电影理解。
摘要：
本文介绍了MovieCORE，一个新颖的视频问答（VQA）数据集，旨在探究对电影内容的更深层认知理解。与关注表层理解的现有数据集不同，MovieCORE强调涉及系统2（System-2）思维且与视频素材保持特定相关性的问题。我们提出了一种创新的智能体头脑风暴方法，利用多个大型语言模型（LLM）作为思维智能体来生成和完善高质量的问答对。为评估数据集质量，我们开发了一套认知测试，评估深度、启发思考潜力和句法复杂性。我们还提出了一套综合评估方案，用于评估VQA模型在更深层次认知任务上的表现。为解决现有视频语言模型（VLM）的局限性，我们引入了智能体增强模块Agentic Choice Enhancement（ACE），该模块在训练后可将模型推理能力提升高达25%。我们的工作有助于推进AI系统对电影的理解，并提供了关于当前VQA模型在面对更具挑战性、更细致的电影内容问题时能力与局限性的宝贵见解。我们的项目页面、数据集和代码可在https://joslefaure.github.io/assets/html/moviecore.html找到。
英文摘要：
This paper introduces MovieCORE, a novel video question answering (VQA) dataset designed to probe deeper cognitive understanding of movie content. Unlike existing datasets that focus on surface-level comprehension, MovieCORE emphasizes questions that engage System-2 thinking while remaining specific to the video material. We present an innovative agentic brainstorming approach, utilizing multiple large language models (LLMs) as thought agents to generate and refine high-quality question-answer pairs. To evaluate dataset quality, we develop a set of cognitive tests assessing depth, thought-provocation potential, and syntactic complexity. We also propose a comprehensive evaluation scheme for assessing VQA model performance on deeper cognitive tasks. To address the limitations of existing video-language models (VLMs), we introduce an agentic enhancement module, Agentic Choice Enhancement (ACE), which improves model reasoning capabilities post-training by up to 25%. Our work contributes to advancing movie understanding in AI systems and provides valuable insights into the capabilities and limitations of current VQA models when faced with more challenging, nuanced questions about cinematic content. Our project page, dataset and code can be found at https://joslefaure.github.io/assets/html/moviecore.html.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
