VideoVista-CulturalLingo：360°视野——弥合视频理解中的文化、语言与领域鸿沟
VideoVista-CulturalLingo: 360$^\circ$ Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension
AI总结：
本研究提出首个跨文化、跨语言、跨领域的视频理解评估基准VideoVista-CulturalLingo，覆盖中欧美文化、中英双语及数百个领域，评估24款视频大模型后发现现有模型存在文化偏向、时序理解弱等问题。
摘要：
评估多模态AI系统的视频理解能力，可有效衡量其理解与推理水平。现有多数视频评估基准仅支持单一语言（通常为英语），且视频内容大多源自西方文化语境。本文提出VideoVista-CulturalLingo，这是首个旨在弥合视频理解领域文化、语言与领域差异的视频评估基准。本工作与现有基准的区别在于：1）文化多样性，纳入了中国、北美与欧洲的文化内容；2）多语言支持，以使用最广泛的两种语言——中文和英文呈现问题；3）领域广泛，视频来自数百个人类创作的领域。VideoVista-CulturalLingo包含1389个视频与3134个问答对，我们已对24个近期的开源或专有视频大模型进行了评估。实验结果显示：1）现有模型在以中文为核心的问题上表现差于以西方为核心的问题，尤其是与中国历史相关的问题；2）当前开源模型在时序理解上仍存在局限，在事件定位任务中表现尤为明显，最高得分仅为45.2%；3）主流模型在通用科学问题上表现优异，而开源模型在数学问题上表现较弱。
英文摘要：
Assessing the video comprehension capabilities of multimodal AI systems can effectively measure their understanding and reasoning abilities. Most video evaluation benchmarks are limited to a single language, typically English, and predominantly feature videos rooted in Western cultural contexts. In this paper, we present VideoVista-CulturalLingo, the first video evaluation benchmark designed to bridge cultural, linguistic, and domain divide in video comprehension. Our work differs from existing benchmarks in the following ways: 1) Cultural diversity, incorporating cultures from China, North America, and Europe; 2) Multi-linguistics, with questions presented in Chinese and English-two of the most widely spoken languages; and 3) Broad domain, featuring videos sourced from hundreds of human-created domains. VideoVista-CulturalLingo contains 1,389 videos and 3,134 QA pairs, and we have evaluated 24 recent open-source or proprietary video large models. From the experiment results, we observe that: 1) Existing models perform worse on Chinese-centric questions than Western-centric ones, particularly those related to Chinese history; 2) Current open-source models still exhibit limitations in temporal understanding, especially in the Event Localization task, achieving a maximum score of only 45.2%; 3) Mainstream models demonstrate strong performance in general scientific questions, while open-source models demonstrate weak performance in mathematics.
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。
