CoChat

Motion Magnified 3-D Residual-in-Dense Network for DeepFake Detection

Mehra, Aman, Agarwal, Akshay, Vatsa, Mayank, Singh, Richa · 2023 · IEEE Transactions on Biometrics, Behavior, and Identity Science
Cited by 45

The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.

Abstract

Driven by the advances in deep learning, highly photo-realistic techniques capable of switching the identity and expression of faces have emerged. Cheap access to computing has brought such technology within the reach of anyone with a computer and Internet including people with sinister motives. To detect these forgeries, we present a novel compression resilient approach for deepfake detection in videos. The proposed approach employs motion magnification as a pre-processing step to amplify temporal inconsistencies common in forged videos. Utilizing these processed videos, we propose the 3D Residual-in-Dense ConvNet, which captures low level spatiotemporal features, which help classify a video as pristine or forged. The proposed method yields more than 93% average detection accuracy on the high compression variant of the FaceForensics++ dataset and achieves state-of-the-art performance on multiple benchmarks across the FaceForensics++ and CelebDF datasets. Further, we study the behavior of deepfake detection algorithms across ethnicities and demonstrate how the proposed method reduces the inherent bias against minority ethnicities prevalent in existing algorithms.

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/tbiom.2022.3201887

Cites

25 of 25 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 25 references

Research works printed but not linked: 40

  1. 10.1109/FG52635.2021.9666937 · DOI
  2. 10.3389/frai.2021.643424 · DOI
  3. Agarwal, Protecting world leaders against deep fakes, 38
  4. 10.1145/3130800.3130818 · DOI · Paper page
  5. 10.1145/133994.134003 · DOI · Paper page
  6. 10.1109/ICME51207.2021.9428361 · DOI · Paper page
  7. 10.1145/2070781.2024164 · DOI · Paper page
  8. 2020, Deepfakes
  9. Dufour, 2019, Contributing data to deepfake detection research
  10. 10.1007/BF01115465 · DOI · Paper page
  11. 10.1109/CVPR.2014.537 · DOI · Paper page
  12. 10.1111/cgf.12552 · DOI · Paper page
  13. Goodfellow, Generative adversarial nets, 1
  14. 10.1109/AVSS.2018.8639163 · DOI · Paper page
  15. 10.1109/CVPR.2018.00745 · DOI · Paper page
  16. 10.1109/CVPR.2017.243 · DOI · Paper page
  17. Karras, Progressive growing of GANs for improved quality, stability, and variation, 1
  18. 10.1109/cvpr.2019.00453 · DOI · Paper page
  19. 10.1109/WACV45572.2020.9093628 · DOI · Paper page
  20. Li, Faceshifter: Towards high fidelity and occlusion aware face swapping, 1
  21. 10.1145/3394171.3414034 · DOI · Paper page
  22. 10.1145/1073204.1073223 · DOI · Paper page
  23. 10.1007/978-3-030-87664-7_17 · DOI
  24. 10.1609/aaai.v35i18.17919 · DOI
  25. Nagpal, 2019, Deep learning for face recognition: Pride or prejudiced?
  26. Nguyen, 2019, Use of a capsule network to detect fake images and videos
  27. 10.1007/978-3-030-01225-0_39 · DOI · Paper page
  28. Petrov, 2020, DeepFaceLab: A simple, flexible and extensible face swapping framework
  29. 10.1007/978-3-642-01793-3_21 · DOI · Paper page
  30. 10.1109/CVPR.2015.7298682 · DOI · Paper page
  31. 10.1109/ICCV.2017.74 · DOI · Paper page
  32. 10.1609/aaai.v34i09.7085 · DOI
  33. 10.1145/3072959.3073640 · DOI · Paper page
  34. 10.1145/3306346.3323035 · DOI · Paper page
  35. 10.1109/ICCV.2015.510 · DOI · Paper page
  36. Wang, 2020, Exposing deep-faked videos by anomalous co-motion pattern detection
  37. 10.1145/1141911.1142010 · DOI
  38. 10.1109/FG47880.2020.00089 · DOI · Paper page
  39. 10.1145/2185520.2185561 · DOI · Paper page
  40. 10.1109/CVPR46437.2021.00222 · DOI · Paper page

Cited by

See all 45

Metadata

Authors
Mehra, A., Agarwal, A., Vatsa, M., & Singh, R.
Venue
IEEE Transactions on Biometrics, Behavior, and Identity Science
Published
2023-01
Volume
5
Issue
1
Pages
39-52
ISSN
2637-6407 (ISSN-L)
OpenAlex
W4293812058
Cited by
45
References
25
FWCI
3.08
Type
journal article
Language
en
Open access
closed
Funders
  • Research Grant from the Government of India
  • Government of India through the Swarnajayanti Fellowship

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: Motion Magnified 3-D Residual-in-Dense Network for DeepFake Detection. https://app.cochat.ai/papers/10.1109/tbiom.2022.3201887
The paper
Mehra, A., Agarwal, A., Vatsa, M., & Singh, R. (2023). Motion Magnified 3-D Residual-in-Dense Network for DeepFake Detection. IEEE Transactions on Biometrics, Behavior, and Identity Science. https://doi.org/10.1109/tbiom.2022.3201887

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.