OpenForensics: Multi-Face Forgery Detection And Segmentation In-The-Wild Dataset [V.1.0.0]

Trung-Nghia Le, Huy H. Nguyen, Junichi Yamagishi, Isao EchizenZenodo 2021 · DOI · OpenAlex

Abstract

OpenForensics is the first large-scale dataset posing a high level of challenges. This dataset is designed with face-wise rich annotations explicitly for face forgery detection and segmentation. With its rich annotations, OpenForensics dataset has great potentials for research in both deepfake prevention and general human face detection. Project Page: https://sites.google.com/view/ltnghia/research/openforensics
BibTeX
@inproceedings{le2021openforensics,
  author = {Trung-Nghia Le and Huy H. Nguyen and Junichi Yamagishi and Isao Echizen},
  title = {{OpenForensics: Multi-Face Forgery Detection And Segmentation In-The-Wild Dataset [V.1.0.0]}},
  booktitle = {Zenodo},
  year = {2021},
  doi = {10.5281/zenodo.5528418},
}

Loading related content...

Figure