通过时空似然进行生成视频的训练无关检测
Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
提出一种无需训练、基于时空似然评分的零样本合成视频检测器，可复用其概率框架对视频的时空一致性进行建模，用于检测任务或作为生成质量评估的参考。
原文依据 We introduce STALL, a simple, training-free, theoretically justified detector that provides likelihood-based scoring for videos, jointly modeling spatial and temporal evidence within a probabilistic framework.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着文本和图像生成领域的重大进展，视频领域也迅猛发展，产生了高度逼真且可控的序列。伴随这一进步，这些模型也引发了对虚假信息的严重担忧，使得对合成视频的可靠检测日益关键。基于图像的检测器从根本上受限于逐帧操作且忽略时序动态，而有监督的视频检测器对未见生成器的泛化能力差，鉴于新模型的快速涌现，这是一个关键缺陷。这些挑战推动了零样本方法的发展，此类方法避免使用合成数据，转而依据真实数据统计对内容进行评分，从而实现无需训练、与模型无关的检测。我们提出了STALL，一个简单、无需训练且具有理论依据的检测器，为视频提供基于似然的评分，在概率框架内联合建模空间与时序证据。我们在两个公开基准上评估了STALL，并引入了ComGenVid，一个包含最优生成模型的新基准。STALL始终优于先前的基于图像和基于视频的基线。代码和数据见：https://omerbenhayun.github.io/stall-video。
英文原文摘要 1201 字符
Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making reliable detection of synthetic videos increasingly crucial. Image-based detectors are fundamentally limited because they operate per frame and ignore temporal dynamics, while supervised video detectors generalize poorly to unseen generators, a critical drawback given the rapid emergence of new models. These challenges motivate zero-shot approaches, which avoid synthetic data and instead score content against real-data statistics, enabling training-free, model-agnostic detection. We introduce STALL, a simple, training-free, theoretically justified detector that provides likelihood-based scoring for videos, jointly modeling spatial and temporal evidence within a probabilistic framework. We evaluate STALL on two public benchmarks and introduce ComGenVid, a new benchmark with state-of-the-art generative models. STALL consistently outperforms prior image- and video-based baselines. Code and data are available at: https://omerbenhayun.github.io/stall-video.