Did You Steal My Shot? Pioneering Camera Motion Plagiarism Detection in Generative Videos

Title: Did You Steal My Shot? Pioneering Camera Motion Plagiarism Detection in Generative Videos 标题： 窃取了我的镜头吗？生成式视频中摄像机运动抄袭检测的开创性研究

Abstract: Camera motion often reflects directorial intent and requires professional equipment, making it a high value form of intellectual property. However, generative video models can imitate such high value camera motions with simple prompts, while existing similarity detection methods mainly operate on visual content and fail to capture deeper motion similarity. This is mainly because their training data entangles camera motion with visual content. Moreover, traditional optical flow is insufficient to represent complex camera motions. 摘要： 摄像机运动往往反映了导演的意图，且需要专业设备支持，因此它是一种高价值的知识产权。然而，生成式视频模型可以通过简单的提示词模仿这种高价值的摄像机运动，而现有的相似度检测方法主要针对视觉内容，无法捕捉到更深层的运动相似性。这主要是因为它们的训练数据将摄像机运动与视觉内容纠缠在了一起。此外，传统的光流法不足以表征复杂的摄像机运动。

We therefore build the first benchmark for camera motion analysis, including a motion dataset with 11 motion styles and evaluation protocols. Furthermore, we propose a motion representation that augments optical flow with vorticity cues from fluid dynamics, thereby better capturing motions. Experiments show that our detector achieves a 3.02* improvement in plagiarism detection over the strongest baseline and remains effective on generative videos. We believe our work extends copyright protection beyond static content to dynamic camera motion. 因此，我们构建了首个摄像机运动分析基准，包括一个包含 11 种运动风格的运动数据集和评估协议。此外，我们提出了一种运动表征方法，通过流体力学中的涡度线索增强光流，从而更好地捕捉运动特征。实验表明，我们的检测器在抄袭检测方面比最强的基准模型提升了 3.02*，并且在生成式视频上依然有效。我们相信，这项工作将版权保护的范围从静态内容扩展到了动态摄像机运动。

---

Paper Details:

• Authors: Chengguo Zhang, Ping Ping
• Date: 8 Sep 2026
• Subjects: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
• DOI: 10.48550/arXiv.2609.22267

论文详情：

• 作者： Chengguo Zhang, Ping Ping
• 日期： 2026年9月8日
• 学科： 计算机视觉与模式识别 (cs.CV)；多媒体 (cs.MM)
• DOI： 10.48550/arXiv.2609.22267