CoCoVideo：面向AI生成视频检测的基于商用模型的高质量对比基准
CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection
提供了基于13个商用生成器的语义对齐真假视频对，可用于训练和评测高保真AIGC视频检测器；其「R3D-18时空特征+置信度门控路由到MLLM推理物理合理性」的框架，为在视觉检测中引入多模态大模型推理提供了可复用的设计范式。
原文依据 we introduce CoCoVideo-26K, a contrastive, commercial-model-based AIGC video dataset covering 13 mainstream commercial generators
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人工智能生成内容（AIGC）技术的快速发展，视频伪造日益普遍，对公共话语和社会安全构成了新的挑战。尽管现有深度伪造检测方法取得了显著进展，但AIGC伪造检测仍具挑战性，因为现有数据集主要依赖开源视频生成模型，其质量远低于商用AIGC系统。即便是包含少量商用样本的数据集，也往往保留可见水印，损害了真实性，并阻碍模型向高保真AIGC视频的泛化。为解决这些问题，我们提出了CoCoVideo-26K，这是一个基于商用模型的对比式AIGC视频数据集，覆盖13个主流商用生成器，并提供语义对齐的真实—伪造视频对。该数据集使得更深入地探索真实视频与高质量合成视频之间的差异成为可能，并为高度逼真的视频伪造检测建立了新的基准。基于该数据集，我们提出了CoCoDetect，一个将对比学习与置信度门控的多模态大语言模型（MLLM）推理相结合的检测框架。R3D-18骨干网络提取时空表征，而置信度门控将不确定样本路由至MLLM，以推理物理合理性与场景一致性。在CoCoVideo-26K和公开基准上的大量实验证明了最优性能，验证了该框架的鲁棒性与泛化能力。我们的代码与数据集见 https://github.com/DonoToT/CoCoVideo。
英文原文摘要 1604 字符
With the rapid advancement of artificial intelligence generated content (AIGC) technologies, video forgery has become increasingly prevalent, posing new challenges to public discourse and societal security. Despite remarkable progress in existing deepfake detection methods, AIGC forgery detection remains challenging, as existing datasets mainly rely on open-source video generation models with quality far below commercial AIGC systems. Even datasets containing a few commercial samples often retain visible watermarks, compromising authenticity and hindering model generalization to high-fidelity AIGC videos. To address these issues, we introduce CoCoVideo-26K, a contrastive, commercial-model-based AIGC video dataset covering 13 mainstream commercial generators and providing semantically aligned real-fake video pairs. This dataset enables deeper exploration of the differences between authentic and high-quality synthetic videos, establishes a new benchmark for highly realistic video forgery detection. Building on this dataset, we propose CoCoDetect, a detection framework integrating contrastive learning with confidence-gated multimodal large language model (MLLM) inference. An R3D-18 backbone extracts spatio-temporal representations, while a confidence gate routes uncertain cases to an MLLM for reasoning about physical plausibility and scene consistency. Extensive experiments on CoCoVideo-26K and public benchmarks demonstrate state-of-the-art performance, validating the framework's robustness and generality. Our code and dataset are available at https://github.com/DonoToT/CoCoVideo.