Skip to content

Dataset · huahua123313

Lip-sync deepfake detection dataset (LipFD)

huahua123313/LipFD

An image dataset accompanying a NeurIPS 2024 paper for detecting lip-sync deepfakes.

What's inside

Materials for the research paper "Lips Are Lying" (NeurIPS 2024) focusing on detecting audio-visual mismatches in lip-movement substitutions. The dataset contains 10,000 to 100,000 images.

What you can do with it

  • Training computer vision models to detect lip-sync deepfakes
  • Validating video fraud protection systems
Size
10K–100K rows
Downloads this month
31.2K
Likes
0

How to load it

from datasets import load_dataset

ds = load_dataset("huahua123313/LipFD")