[2505.22564] PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion

Computer Science > Computer Vision and Pattern Recognition arXiv:2505.22564 (cs) [Submitted on 28 May 2025 (v1), last revised 24 Mar 2026 (this version, v2)] Title:PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion Authors:Jaehyun Choi, Jiwan Hur, Gyojin Han, Jaemyung Yu, Junmo Kim View a PDF of the paper titled PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion, by Jaehyun Choi and 4 other authors View PDF HTML (experimental) Abstract: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 identifie...