CoChat

MRE-Net: Multi-Rate Excitation Network for Deepfake Video Detection

Pang, Guilin, Zhang, Baopeng, Teng, Zhu, Qi, Zige, Fan, Jianping · 2023 · IEEE Transactions on Circuits and Systems for Video Technology
Cited by 72

The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.

Abstract

The current social media is flooded with hyper realistic face-synthetic videos due to the explosion of DeepFake technology that has brought a serious impact on human society security, which calls for further exploring on deepfake video detection methods. Existing methods attempt to isolated capture spatial artifacts or extract the homogeneous temporal inconsistency to detect deepfake video, but little attention has been paid to the exploitation of dynamic spatial-temporal inconsistency. To mitigate this issue, in this paper, we propose a novel Multi-Rate Excitation Network (MRE-Net) to effectively excite dynamic spatial-temporal inconsistency from the perspective of multiple rates for deepfake video detection. The proposed MRE-Net is composed of two components: Bipartite Group Sampling (BGS) and multiple rate branches. The BGS draws the entire video into multiple bipartite groups with different rates to cover various face motion dynamic evolution. We further design multiple rate branches to capture both short-term and long-term spatial-temporal inconsistency from corresponding bipartite groups of BGS. Concretely, for the early stages of the multi-rate branches, Momentary Inconsistency Excitation (MIE) module is developed to encode the spatial artifacts and intra-group short-term temporal inconsistency. Meanwhile, for the last stages of the multi-rate branches, Longstanding Inconsistency Excitation (LIE) module is constructed to perceive inter-group long-term temporal dynamics. Extensive experiments and visualizations conducted on four popular datasets demonstrate the effectiveness of the proposed method against state-of-the-art deepfake detection methods.

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/tcsvt.2023.3239607

Cites

33 of 33 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 33 references

Research works printed but not linked: 28

  1. 10.1109/TPAMI.2020.3034267 · DOI · Paper page
  2. Karras, 2017, Progressive growing of GANs for improved quality, stability, and variation, arXiv:1710.10196 · arXiv
  3. 10.1016/j.patcog.2021.107950 · DOI · Paper page
  4. 10.1109/CVPR.2017.195 · DOI · Paper page
  5. 10.1109/TIFS.2022.3146781 · DOI · Paper page
  6. 10.1109/TCSVT.2021.3133859 · DOI · Paper page
  7. Tariq, 2020, A convolutional LSTM based residual network for deepfake video detection, arXiv:2009.07480 · arXiv
  8. 10.1109/AVSS.2018.8639163 · DOI · Paper page
  9. de Lima, 2020, Deepfake detection using spatiotemporal convolutional networks, arXiv:2006.14749 · arXiv
  10. 10.1109/WIFS.2013.6707813 · DOI
  11. 10.1109/TIFS.2013.2265677 · DOI · Paper page
  12. 10.1109/TIFS.2012.2202227 · DOI · Paper page
  13. 10.1109/TIFS.2015.2394231 · DOI · Paper page
  14. 10.1007/s11042-010-0620-1 · DOI · Paper page
  15. 10.1109/WIFS.2015.7368565 · DOI · Paper page
  16. 10.1016/j.ins.2020.11.026 · DOI
  17. 10.1109/TMM.2021.3073267 · DOI
  18. 2020, Deepfakes Github
  19. 10.1145/3306346.3323035 · DOI · Paper page
  20. 10.1109/tcsvt.2022.3217950 · DOI · Paper page
  21. 10.1007/978-3-031-19781-9_2 · DOI
  22. 10.1109/TCSVT.2022.3177238 · DOI
  23. 10.1109/TCSVT.2021.3074259 · DOI · Paper page
  24. 10.1007/978-3-642-35289-8_25 · DOI · Paper page
  25. Tan, EfficientNet: Rethinking model scaling for convolutional neural networks, 6105
  26. 10.1109/ICCV.2015.510 · DOI · Paper page
  27. Van der Maaten, 2008, Visualizing data using t-SNE, J. Mach. Learn. Res., 9, 1
  28. 10.1109/ICCV.2017.74 · DOI · Paper page

Cited by

See all 72

Metadata

Authors
Pang, G., Zhang, B., Teng, Z., Qi, Z., & Fan, J.
Venue
IEEE Transactions on Circuits and Systems for Video Technology
Published
2023-08
Volume
33
Issue
8
Pages
3663-3676
ISSN
  • 1051-8215 (ISSN-L)
  • 1558-2205
OpenAlex
W4317987748
Cited by
72
References
33
FWCI
6.55
Type
journal article
Language
en
Open access
closed
Funders
  • Fundamental Research Funds for the Central Universities of China (2022JBMC009)
  • Natural Science Foundation of China (61972027)
  • Beijing Municipal Natural Science Foundation (4212041)

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: MRE-Net: Multi-Rate Excitation Network for Deepfake Video Detection. https://app.cochat.ai/papers/10.1109/tcsvt.2023.3239607
The paper
Pang, G., Zhang, B., Teng, Z., Qi, Z., & Fan, J. (2023). MRE-Net: Multi-Rate Excitation Network for Deepfake Video Detection. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/tcsvt.2023.3239607

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.