CoChat

Extracting Deep Local Features to Detect Manipulated Images of Human Faces

Open access
Tarasiou, Michail, Zafeiriou, Stefanos · 2020 · 2020 IEEE International Conference on Image Processing (ICIP)
Cited by 21

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Abstract

Recent developments in computer vision and machine learning have made it possible to create realistic manipulated videos of human faces, raising the issue of ensuring adequate protection against the malevolent effects unlocked by such capabilities. In this paper we propose local image features which are shared across manipulated regions as a key element for the automatic detection of manipulated face images. We also design a lightweight architecture with the correct structural biases for extracting such features and derive a multitask training scheme that consistently outperforms image class supervision alone. The trained networks achieve state-of-the-art results in the FaceForensics++ dataset using significantly reduced number of parameters and are shown to work well in detecting fully generated face images.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icip40778.2020.9190714

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 13 references

Research works printed but not linked: 15

  1. agarwal, 2019, Protecting World Leaders Against Deep Fakes, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 8
  2. lin, 2013, Network in Network
  3. nair, 2010, Rectified linear units improve restricted boltzmann machines, Proceedings of the 27th International Conference on International Conference on Machine Learning, 807
  4. ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, CoRR, abs 1502 3167
  5. goodfellow, 2014, Generative adversarial nets, Advances in neural information processing systems, 27, 2672
  6. 10.1145/3292039 · DOI · Paper page
  7. karras, 2018, A style-based generator architecture for generative adversarial networks, CoRR, abs 1812 4948
  8. karras, 2017, Progressive growing of gans for improved quality, stability, and variation, CoRR, abs 1710 10196
  9. 0, Deepfakes github
  10. kowalski, 0, Faceswap
  11. rahmouni, 2017, Distinguishing computer graphics from natural images using convolution neural networks, IEEE Workshop on Information Forensics and Security (WIFS) 2010, 1
  12. rössler, 2018, Faceforensics: A large-scale video dataset for forgery detection in human faces, CoRR, abs 1803 9179
  13. alexey, 2019, Deepfakes detection dataset by google & jigsaw
  14. deng, 2019, Retinaface: Single-stage dense face localisation in the wild, CoRR, abs 1905 641
  15. li, 2019, Celeb-DF A new dataset for deepfake forensics

Cited by

See all 21

Metadata

Authors
Tarasiou, M., & Zafeiriou, S.
Venue
2020 IEEE International Conference on Image Processing (ICIP)
Publisher
IEEE
Published
2020-10
Pages
1821-1825
ISSN
1522-4880 (ISSN-L)
OpenAlex
W3006015659
Cited by
21
References
13
FWCI
1.05
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Extracting Deep Local Features to Detect Manipulated Images of Human Faces. https://app.cochat.ai/papers/10.1109/icip40778.2020.9190714
The paper
Tarasiou, M., & Zafeiriou, S. (2020). Extracting Deep Local Features to Detect Manipulated Images of Human Faces. 2020 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip40778.2020.9190714

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.