LongVQUBench：评估视觉语言模型的长期视频质量理解能力
LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models
AI总结：
提出LongVQUBench基准，包含1200+长视频和1500个问题，通过三级评估（局部、跨事件、全局）和针孔失真问答范式，揭示现有LVLMs在长视频质量理解上的局限性。
摘要：
长期视频质量理解的评估对于大型视觉语言模型（LVLMs）仍是一个开放挑战。现有的视频质量基准主要关注短片段和孤立失真，忽视了长视频内容中固有的时间连续性、累积退化和推理复杂性。为解决这些局限，我们提出了LongVQUBench，一个用于长期视频质量理解的综合基准。LongVQUBench包含超过1200个多样化视频，涵盖电影、纪录片、监控录像、自我中心记录和动画内容，并配有1500个用于验证和测试的多选题和开放性问题。为了评估不同时间范围内的感知推理，我们引入了三个逐步复杂的评估级别：（i）局部事件质量理解（LQU），用于分析局部失真；（ii）跨事件质量推理（CQR），用于整合多个退化事件；（iii）全局质量理解（GQU），用于长时间跨度的整体感知评估。此外，在所有三个级别中嵌入了针孔失真问答（NDQA）范式，其中稀疏地插入空间或时间伪影以探测细粒度的检测和推理能力。对14个最先进LVLMs的大量实验表明，随着视频长度和推理深度的增加，性能显著下降，突显了它们在长程时间整合和感知归因方面的有限能力。我们期望LongVQUBench成为系统化、层次化和可解释地评估LVLMs长期视频质量理解能力的基础步骤。
英文摘要：
The evaluation of long-term video quality understanding remains an open challenge for large vision-language models (LVLMs). Existing video quality benchmarks predominantly focus on short clips and isolated distortions, overlooking the temporal continuity, cumulative degradation, and reasoning complexity inherent in long-duration content. To address these limitations, we present LongVQUBench, a comprehensive benchmark for long-term video quality understanding. LongVQUBench contains over 1200 diverse videos spanning movies, documentaries, surveillance footage, egocentric recordings, and animated content, accompanied by 1500 multiple-choice and open-ended questions for validation and testing. To assess perceptual reasoning across different temporal scopes, we introduce three progressively complex evaluation levels: (i) local event quality understanding (LQU) for analyzing localized distortions; (ii) cross-event quality reasoning (CQR) for integrating multiple degraded events; and (iii) global quality understanding (GQU) for holistic perceptual evaluation over extended durations. Furthermore, a needle distortion question-answering (NDQA) paradigm is embedded across all three levels, where spatial or temporal artifacts are sparsely inserted to probe fine-grained detection and reasoning capabilities. Extensive experiments on 14 state-of-the-art LVLMs reveal significant performance degradation with increasing video length and reasoning depth, highlighting their limited capacity for long-range temporal integration and perceptual attribution. We envision LongVQUBench as a foundational step toward the systematic, hierarchical, and explainable evaluation of LVLMs' long-term video quality understanding.
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。
