ViKey：通过视觉提示增强视频时序理解
ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting
提出一种免训练的视觉提示方法，通过在帧上叠加序号信息增强VideoLLM的时序理解，可复用于任何稀疏采样视频理解流程，缓解帧选择带来的时序推理性能下降。
原文依据 we explore visual prompting (VP) as a lightweight yet effective way to enhance temporal understanding in VideoLLMs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期视频大语言模型（VideoLLMs）的进展使其在多种多模态视频任务上表现出强大性能。为降低处理密集视频帧的高计算成本，帧选择等效率导向方法已被广泛采用。这些方法虽能有效减少冗余，但往往导致需要时序推理的任务性能显著下降。与人类能从稀疏视觉线索推断事件进展不同，VideoLLMs在中间帧被省略时经常误解时序关系。为解决这一局限，我们探索视觉提示（VP）作为一种轻量而有效的方式来增强VideoLLMs的时序理解。我们的分析表明，简单地为每帧标注显式序号信息有助于模型感知时序连续性。这一视觉线索还支持帧级引用，并缓解稀疏采样序列中的位置歧义。基于这些发现，我们提出ViKey，一个免训练框架，将VP与轻量级关键词-帧映射（KFM）模块相结合。KFM利用帧索引作为字典式键，将文本线索链接到最相关的帧，在推理时提供显式时序锚点。尽管方法简单，我们的方法显著提升了时序推理能力，并在部分数据集上仅用20%的帧就保持了密集帧基线的性能。
英文原文摘要 1460 字符
Recent advancements in Video Large Language Models (VideoLLMs) have enabled strong performance across diverse multimodal video tasks. To reduce the high computational cost of processing dense video frames, efficiency-oriented methods such as frame selection have been widely adopted. While effective at minimizing redundancy, these methods often cause notable performance drops on tasks requiring temporal reasoning. Unlike humans, who can infer event progression from sparse visual cues, VideoLLMs frequently misinterpret temporal relations when intermediate frames are omitted. To address this limitation, we explore visual prompting (VP) as a lightweight yet effective way to enhance temporal understanding in VideoLLMs. Our analysis reveals that simply annotating each frame with explicit ordinal information helps the model perceive temporal continuity. This visual cue also supports frame-level referencing and mitigates positional ambiguity within a sparsely sampled sequence. Building on these insights, we introduce ViKey, a training-free framework that combines VP with a lightweight Keyword-Frame Mapping (KFM) module. KFM leverages frame indices as dictionary-like keys to link textual cues to the most relevant frames, providing explicit temporal anchors during inference. Despite its simplicity, our approach substantially improves temporal reasoning and, on some datasets, preserves dense-frame baseline performance with as few as 20% of frames.