VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
Jiaqi Wang, Weijia Wu, Yi Zhan, Rui Zhao, Ming Hu, James Cheng, Wei Liu, Philip Torr, Kevin Qinghong Lin

TL;DR
VideoASMR-Bench is a new benchmark for evaluating AI-generated ASMR videos' realism and detection, revealing current models' limitations in discerning synthetic from real videos and vice versa.
Contribution
The paper introduces VideoASMR-Bench, a diverse dataset and an adversarial evaluation framework for assessing AI-generated ASMR videos and detection capabilities.
Findings
State-of-the-art VLMs struggle to detect AI-generated ASMR videos.
Current video generation models can produce convincing ASMR videos.
Humans still outperform models in identifying fake ASMR videos.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
