Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 71 of the 83 references it cites were found in a registry or an index.

PVASS-MDD: Predictive Visual-Audio Alignment Self-Supervision for Multimodal Deepfake Detection

Yu, Yang, Liu, Xiaolong, Ni, Rongrong, Yang, Siyuan, Zhao, Yao, Kot, Alex C. · 2024 · IEEE Transactions on Circuits and Systems for Video Technology

Abstract

Deepfake techniques can forge the visual or audio signals in the video, which leads to inconsistencies between visual and audio (VA) signals. Therefore, multimodal detection methods expose deepfake videos by extracting VA inconsistencies. Recently, deepfake technology has started VA collaborative forgery to obtain more realistic deepfake videos, which poses new challenges for extracting VA inconsistencies. Recent multimodal detection methods propose to first extract natural VA correspondences in real videos in a self-supervised manner, and then use the learned real correspondences as targets to guide the extraction of VA inconsistencies in the subsequent deepfake detection stage. However, the inherent VA relations are difficult to extract due to the modality gap, which leads to the limited auxiliary performance of the aforementioned self-supervised methods. In this paper, we propose Predictive Visual-audio Alignment Self-supervision for Multimodal Deepfake Detection (PVASS-MDD), which consists of PVASS auxiliary and MDD stages. In the PVASS auxiliary stage in real videos, we first devise a three-stream network to associate two augmented visual views with corresponding audio clues, leading to explore common VA correspondences based on cross-view learning. Secondly, we introduce a novel cross-modal predictive align module for eliminating VA gaps to provide inherent VA correspondences. In the MDD stage, we propose to the auxiliary loss to utilize the frozen PVASS network to align VA features of real videos, to better assist multimodal deepfake detector for capturing subtle VA inconsistencies. We conduct extensive experiments on existing widely used and latest multimodal deepfake datasets. Our method obtains a significant performance improvement compared to state-of-the-art methods.

Overview

Integrity signals

Registry

Crossref · 10.1109/tcsvt.2023.3309899

Cites

71 of 71 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 83 references

Research works printed but not linked: 2

  1. 2020, Faceswap
  2. 2020, Deepfakes

Cited by

See all 63

Metadata

Authors
Yu, Y., Liu, X., Ni, R., Yang, S., Zhao, Y., & Kot, A. C.
Affiliations
  • Beijing Jiaotong University (CN)
  • Nanyang Technological University (SG)
Venue
IEEE Transactions on Circuits and Systems for Video Technology
Published
2024-08
Volume
34
Issue
8
Pages
6926-6936
ISSN
  • 1051-8215 (ISSN-L)
  • 1558-2205
OpenAlex
W4386267173
Cited by
63
References
83
Citations by year
2026: 26 · 2025: 24 · 2024: 11
FWCI
5.70
Type
journal article
Language
en
Open access
closed
Locations
  • IEEE Transactions on Circuits and Systems for Video Technology (publishedVersion)
  • DR-NTU (Nanyang Technological University) (submittedVersion)
Funders
  • National Key Research and Development Program of China (2021ZD0112100)
  • National NSF of China (62336001, U1936212, 62120106009)
  • Beijing NSF (4222014)
  • Rapid-Rich Object Search (ROSE) Laboratory, Nanyang Technological University, Singapore
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
Keywords
deepfake detection, self-supervised learning, modality gap

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: PVASS-MDD: Predictive Visual-Audio Alignment Self-Supervision for Multimodal Deepfake Detection. https://app.cochat.ai/papers/10.1109/tcsvt.2023.3309899
The paper
Yu, Y., Liu, X., Ni, R., Yang, S., Zhao, Y., & Kot, A. C. (2024). PVASS-MDD: Predictive Visual-Audio Alignment Self-Supervision for Multimodal Deepfake Detection. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/tcsvt.2023.3309899

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.