PRISM：面向稀疏运动的渐进细化与插入式视频数据集浓缩
PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion
把视频压缩成极少量关键帧加插值来构造蒸馏数据集，这种「按需插入关键帧」的思路可直接迁移到视频训练数据筛选、高效视频预训练和视频 token 压缩等环节。
原文依据 It begins with minimal temporal anchors and progressively inserts key-frames only where linear interpolation fails to capture non-linear dynamics.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频数据集浓缩旨在降低视频处理带来的巨大计算开销。然而，它面临一个根本性挑战，即空间外观与时序动态之间不可分割的相互依赖。已有工作遵循静态/动态解耦范式，将视频分解为静态内容和辅助运动信号。这种多阶段方法往往无法正确刻画真实世界动作的内在耦合关系。我们提出面向稀疏运动的渐进细化与插入方法（PRISM），这是一种整体式方法，从一开始就将视频视为统一且完全耦合的时空结构。为最大化表示效率，PRISM 通过避免固定帧优化来应对视频固有的时序冗余。它从最少量的时序锚点开始，仅在线性插值无法捕捉非线性动态之处渐进地插入关键帧。这些关键帧通过梯度失配来识别。这种自适应过程确保表示容量被精确分配到所需之处，在保留复杂运动的同时最小化存储需求。大量实验表明，PRISM 在标准基准上取得了有竞争力的性能，同时通过其稀疏且整体学习到的表示实现了最优的存储效率。
英文原文摘要 1387 字符
Video dataset condensation aims to reduce the immense computational cost of video processing. However, it faces a fundamental challenge regarding the inseparable interdependence between spatial appearance and temporal dynamics. Prior work follows a static/dynamic disentanglement paradigm where videos are decomposed into static content and auxiliary motion signals. This multi-stage approach often misrepresents the intrinsic coupling of real-world actions. We introduce Progressive Refinement and Insertion for Sparse Motion (PRISM), a holistic approach that treats the video as a unified and fully coupled spatiotemporal structure from the outset. To maximize representational efficiency, PRISM addresses the inherent temporal redundancy of video by avoiding fixed frame optimization. It begins with minimal temporal anchors and progressively inserts key-frames only where linear interpolation fails to capture non-linear dynamics. These critical moments are identified through gradient misalignments. Such an adaptive process ensures that representational capacity is allocated precisely where needed, minimizing storage requirements while preserving complex motion. Extensive experiments demonstrate that PRISM achieves competitive performance across standard benchmarks while providing state-of-the-art storage efficiency through its sparse and holistically learned representation.