NARU：用于理解日语超长视频中叙事演变与文化细微差别的基准
NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video
浏览论文内容
中文总结 AI 辅助
该研究推出NARU基准，涵盖155个146.8小时日语视频的1481个问题，评估模型在长程叙事整合与文化推理上的局限，为MLLM开发提供测试平台。
中文摘要 AI 辅助
长篇视频理解涵盖的任务不止于检索孤立事件，还包括追踪演变中的叙事以及解读可能隐含的社会意义。然而，现有基准很少联合评估这些能力，尤其是在高语境的非英语媒体中。为解决这一差距，我们推出NARU，一个旨在评估日语长篇视频中叙事演变与文化理解推理的基准。NARU包含1481个问题，基于155个总时长146.8小时的视频，涵盖4个叙事维度和5个文化维度。为构建该规模的基准，我们提出一种基于分层记忆的标注流水线，将原始视频转化为结构化的事件、叙事和文化标注，再通过面向任务的合成与迭代捷径消除生成问题。构建过程包含两个母语者验证阶段，涉及68名标注员。对8种模型配置的评估显示，其在长程叙事整合和基于文化的推理方面存在显著局限。通过揭示这些持续存在的差距，NARU为开发能够可靠解读长篇高语境视频的多模态大语言模型（MLLM）提供了系统测试平台。
英文摘要
Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain implicit. However, existing benchmarks rarely evaluate these capabilities jointly, particularly in high-context, non-English media. To address this gap, we introduce NARU, a benchmark designed to evaluate Narrative evolution and Reasoning on cultural Understanding in Japanese long-form video. NARU consists of 1,481 questions grounded in 155 videos totaling 146.8 hours, spanning four narrative and five cultural dimensions. To construct the benchmark at this scale, we propose a hierarchical memory-based annotation pipeline that transforms raw video into structured event, narrative, and cultural annotations, then generates questions via task-oriented synthesis and iterative shortcut removal. The construction process includes two native-speaker verification stages involving 68 annotators. Evaluations across eight model configurations reveal substantial limitations in both long-range narrative integration and culturally grounded reasoning. By exposing these persistent gaps, NARU offers a systematic testing ground for developing MLLMs capable of reliably interpreting long-form, high-context video.
发表机构
- The University of Tokyo（东京大学）
- Kyushu University（九州大学）
- Macau University of Science and Technology（澳门科技大学）
- Infinimind Japan Inc.（Infinimind日本公司）
- University of Alberta（阿尔伯塔大学）
机构由 AI 辅助整理，请以论文原文为准。
