arXiv 2512.132812026-05-07cs.CV

VideoASMR-Bench: AI生成的ASMR视频能否欺骗视觉语言模型和人类？

VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?

The Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；Peking University（北京大学）；Monash University（墨尔本大学）；Video Rebirth；University of Oxford（牛津大学）

Jiaqi Wang, Weijia Wu, Yi Zhan, Rui Zhao, Ming Hu, James Cheng, Wei Liu, Philip Torr, Kevin Qinghong Lin

备注：: Code is at https://github.com/video-reality-test/video-reality-test, page is at https://video-reality-test.github.io/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

VideoASMR-Bench通过细粒度音频视觉感知和感官沉浸性评估AI生成ASMR视频的检测能力，揭示了当前VLMs在识别AI生成ASMR视频上的不足以及VGMs生成逼真ASMR视频的能力。

摘要：

随着AI生成的视频越来越难以与现实区分，当前的基准主要关注广义语义对齐和基本物理一致性，提供有限的判别能力。为此，我们引入VideoASMR-Bench，一个基于自主感官脉冲反应（ASMR）视频的基准，强调细粒度音频视觉感知和感官沉浸性。该基准旨在回答两个关键问题：（i）当今的视频理解模型（VLMs）是否足够敏感，能够通过识别细微的视觉、物理或听觉瑕疵来检测AI生成的ASMR视频？（ii）当今的视频生成模型（VGMs）能否生成具有沉浸体验的ASMR视频？该基准包含来自社交媒体精心挑选的1500个高质量真实ASMR视频，以及由九个VGMs生成的2235个合成视频。此外，我们开源了一套可扩展的提示和参考图像，使基准能够动态扩展以适应未来视频模型。此外，我们设计了一个自动理解-生成评估框架，使VGMs试图生成逼真假视频以欺骗VLMs，而VLMs则试图检测它们，形成双方之间的对抗游戏。在VideoASMR-Bench上的评估表明，即使最先进的VLMs，如Gemini-3-Pro，也未能可靠地检测AI生成的ASMR视频。同时，当前前沿的视频生成模型能够生成难以被VLMs区分的ASMR视频，而人类仍能相对容易地识别它们。

英文摘要：

With AI-generated videos increasingly indistinguishable from reality, current benchmarks primarily focus on broad semantic alignment and basic physical consistency, offering limited discriminative power for evaluating them. To address this, we introduce VideoASMR-Bench, a benchmark based on Autonomous Sensory Meridian Response (ASMR) videos that emphasizes fine-grained audio-visual perception and sensory immersion. This benchmark aims to answer two key questions: (i) Are today's video understanding models (VLMs) sensitive enough to detect AI-generated ASMR videos by recognizing minor visual, physical, or auditory artifacts? (ii) Can today's video generation models (VGMs) produce convincing ASMR videos with immersive experiences? This benchmark comprises a diverse set of 1,500 high-quality real ASMR videos curated from social media, alongside 2,235 synthetic counterparts generated by nine VGMs. Additionally, we open-source an extensible suite of prompts and reference images, enabling the benchmark to scale dynamically with future video models. Moreover, we design an automatic understanding-generation evaluation framework between VGMs and VLMs, where VGMs aim to produce realistic fake videos to fool the VLMs, while the VLMs seek to detect them, forming an adversarial game between the two parties. Our evaluation on VideoASMR-Bench reveals that even state-of-the-art VLMs, such as Gemini-3-Pro, fail to reliably detect AI-generated ASMR videos. Meanwhile, current frontier video generation models can produce ASMR videos that are difficult for VLMs to distinguish from real ones, while humans can still identify them relatively easily.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。