CoChat

A video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes

Wang, Yaohui, Dantcheva, Antitza · 2020 · 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)
Cited by 59

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

Manipulated images and videos have become increasingly realistic due to the tremendous progress of deep convolutional neural networks (CNNs). While technically intriguing, such progress raises a number of social concerns related to the advent and spread of fake information and fake news. Such concerns necessitate the introduction of robust and reliable methods for fake image and video detection. Towards this in this work, we study the ability of state of the art video CNNs including 3D ResNet, 3D ResNeXt, and I3D in detecting manipulated videos. We present related experimental results on videos tampered by four manipulation techniques, as included in the FaceForensics++ dataset. We investigate three scenarios, where the networks are trained to detect (a) all manipulated videos, as well as (b) separately each manipulation technique individually. Finally and deviating from previous works, we conduct cross-manipulation results, where we (c) detect the veracity of videos pertaining to manipulation-techniques not included in the train set. Our findings clearly indicate the need for a better understanding of manipulation methods and the importance of designing algorithms that can successfully generalize onto unknown manipulations.

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/fg47880.2020.00089

Cites

14 of 14 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 14 references

Research works printed but not linked: 25

  1. 10.23919/BIOSIG.2018.8553251 · DOI · Paper page
  2. 10.23919/EUSIPCO.2018.8553270 · DOI · Paper page
  3. 10.1109/CVPR.2018.00685 · DOI · Paper page
  4. 10.1109/CVPR.2017.502 · DOI · Paper page
  5. thies, 2019, Deferred neural rendering: Image synthesis using neural textures, arXiv preprint arXiv 1904 12848
  6. 10.1109/CVPR.2017.195 · DOI · Paper page
  7. 10.1109/WIFS.2017.8267647 · DOI · Paper page
  8. 10.1109/CVPR42600.2020.00531 · DOI · Paper page
  9. 10.1016/j.neucom.2019.05.003 · DOI
  10. averbuch-elor, 2017, Bringing portraits to life, ACM Transactions on Graphics (TOG), 36, 196, 10.1145/3130800.3130818 · DOI · Paper page
  11. 10.23919/BIOSIG.2018.8553377 · DOI
  12. kim, 2018, Deep video portraits, ACM Transactions on Graphics (TOG), 37, 163, 10.1145/3197517.3201283 · DOI · Paper page
  13. silbey, 2018, The upside of deep fakes, Md L Rev, 78, 960
  14. suwajanakorn, 2017, Synthesizing obama: learning lip sync from audio, ACM Transactions on Graphics (TOG), 36, 95, 10.1145/3072959.3073640 · DOI · Paper page
  15. eichensehr, 2018, Don’t believe it if you see it: Deep fakes and distrust, Jotwell J Things We Like, 1
  16. chesney, 2018, Deep fakes: A looming challenge for privacy, democracy, and national security. 107 california law review (2019, forthcoming); u of texas law, Public Law Research Paper, 2018
  17. 10.1145/2929464.2929475 · DOI · Paper page
  18. agarwal, 2019, Protecting world leaders against deep fakes, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 38
  19. farid, 2011, Photo tampering throughout history
  20. wang, 2019, G3AN: This video does not exist. disentangling motion and appearance for video generation, arXiv preprint arXiv 1912 05523
  21. 10.1109/WACV45572.2020.9093492 · DOI · Paper page
  22. goodfellow, 2014, Generative adversarial nets, Advances in neural information processing systems, 2672
  23. xu, 2019, Adversarial attacks and defenses in images, graphs and text: A review, arXiv preprint arXiv 1909 08072
  24. majumdar, 2019, Evading face recognition via partial tampering of faces, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 0
  25. 10.1109/CVPR.2019.00453 · DOI · Paper page

Cited by

See all 59

Metadata

Authors
Wang, Y., & Dantcheva, A.
Venue
2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)
Publisher
IEEE
Published
2020-11
Pages
515-519
ISSN
1541-5058 (ISSN-L)
OpenAlex
W3034785167
Cited by
59
References
14
FWCI
3.41
Type
conference paper
Language
en
Open access
closed

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: A video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes. https://app.cochat.ai/papers/10.1109/fg47880.2020.00089
The paper
Wang, Y., & Dantcheva, A. (2020). A video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes. 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020). https://doi.org/10.1109/fg47880.2020.00089

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.