看见场景才重要：用场景感知长视频基准揭示视频理解模型中的遗忘
Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
SceneBench 把长视频按「视觉与语义上下文一致的场景」切分，并给出场景级问答协议，可直接用于诊断 VLM 的长程遗忘；Scene-RAG 的动态场景记忆检索思路也可迁移到任何需要跨片段取证的视频问答或视频对话系统。
原文依据 we introduce a new benchmark, SceneBench, designed to provide scene-level challenges
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论长视频理解（LVU）仍是多模态学习的核心挑战。尽管近期的视觉语言模型（VLM）取得了显著进展，现有基准主要聚焦于细粒度感知或粗粒度摘要，对长上下文中的时序理解所提供的洞察有限。在本工作中，我们将场景定义为视频中视觉与语义上下文均保持一致的一段连贯片段，这与人类感知相一致。由此引出一个关键问题：当前的 VLM 能否在长程、场景级上下文上有效推理？为回答这一问题，我们提出了一个新的基准 SceneBench，旨在提供场景级挑战。我们的评测显示，当 VLM 尝试回答场景级问题时准确率急剧下降，表明其对长程上下文存在显著的遗忘。为进一步验证这些发现，我们提出了场景检索增强生成（Scene-RAG），它通过跨场景检索并整合相关上下文来构建动态场景记忆。Scene-RAG 使 VLM 性能提升 +2.50%，证实当前模型在长上下文保持方面仍存在困难。我们希望 SceneBench 能推动未来研究，朝向具备更稳健、更接近人类的视频理解能力的 VLM。
英文原文摘要 1269 字符
Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: Can current VLMs reason effectively over long, scene-level contexts? To answer this, we introduce a new benchmark, SceneBench, designed to provide scene-level challenges. Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context. To further validate these findings, we propose Scene Retrieval-Augmented Generation (Scene-RAG), which constructs a dynamic scene memory by retrieving and integrating relevant context across scenes. Scene-RAG improves VLM performance by +2.50%, confirming that current models still struggle with long-context retention. We hope SceneBench will encourage future research toward VLMs with more robust, human-like video comprehension.