VCapAV: A Video-Caption Based Audio-Visual Deepfake Detection Dataset
收藏Zenodo2025-05-25 更新2026-05-26 收录
下载链接：
https://zenodo.org/doi/10.5281/zenodo.15498946
下载链接
链接失效反馈官方服务：
资源简介：
This deposition contains large-scale split archives of the VCapAV dataset. Each component is split using 7-Zip into parts (.7z.001, .7z.002, ...). To extract, download all parts and open the .001 with 7-Zip (https://www.7-zip.org/). VCapAV is a multimodal dataset for environmental audio deepfake detection. More info: https://VCapAV.github.io/
提供机构：
Zenodo创建时间：
2025-05-25
