The DOI matches its Crossref record; 117 of the 117 references it cites were found in a registry or an index.
Self-Supervised Video Forensics by Audio-Visual Anomaly Detection
Open accessAbstract
Manipulated videos often contain subtle inconsistencies between their visual and audio signals. We propose a video forensics method, based on anomaly detection, that can identify these inconsistencies, and that can be trained solely using real, unlabeled data. We train an autoregressive model to generate sequences of audio-visual features, using feature sets that capture the temporal synchronization between video frames and sound. At test time, we then flag videos that the model assigns low probability. Despite being trained entirely on real videos, our model obtains strong performance on the task of detecting manipulated speech videos. Project site: https://cfeng16.github.io/audio-visual-forensics.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The cited source doesn’t support the claim as written.
In the citing paper
“The performance of any deepfake detection method is highly dependent on the quantitative and qualitative aspects of the datasets used for development [18, 21, 25, 40, 44, 47, 49, 51, 52, 61, 63, 69, 72, 75].”
From AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset (2024) · cites this paper as [18]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Existing surveys do not examine how detection methods withstand adversarial attacks designed to evade detection [17, 21] or postprocessing operations that degrade detection performance [22-24].”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [22]
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 6×
“To detect anomalies, we fit an autoregressive generative model [84, 99] to sequences of synchronization features extracted from real videos, and identify low probability examples.”
MethodInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
(2014) · Cited by 33,419
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
The Kinetics Human Action Video DatasetPreprint
Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.06950 · Cited by 5,004
Research works printed but not linked: 4
- radford, 2019, Language models are unsupervised multitask learners, OpenAIRE blog, 1, 9
- zhang, 2017, S3fd: Single shot scale-invariant face detector, Proceedings of the IEEE International Conference on Computer Vision, 192
- 2022, Faceswap
- zong, 2018, Deep auto-encoding gaussian mixture model for unsupervised anomaly detection, International Conference on Learning Representations
Cited by
Sorted by citations
Items 101–103 of 103
Shiohara, K., Yamasaki, T., & Golyanik, V. (2026) · doi:10.1109/cvprf71909.2026.00355
“They quantify the plausibility of input videos based on reconstruction [44], audio-visual consistency [31, 59, 74], and identity consistency with reference sets of specific subjects [17, 18].”
CertAV: Manifold-Aware Certified Robustness for Audio-Visual Deepfake Detection
Parmar, P. J., Bhatt, C., Bharti, S. K., & Desai, T. (2026) · ACM Workshop on Deepfake, Deception, and Disinformation Security (3D-Sec) · doi:10.1145/3843205.3845623
A Unified Ensemble Framework for Detecting Manipulated and AI-Generated Facial Content
Ακριώτη, Α., Pintelas, E. G., Tsakanikas, V., & Tampakas, B. (2026) · Pan-Hellenic Conference on Progress in Computing and Informatics (PCI) · doi:10.1145/3829216.3829255
“The method demonstrates strong cross-data performance, achieving results with AUC scores around 94-95% on datasets such as FakeAVCeleb and KoDF [12].”
Metadata
- Authors
- Feng, C., Chen, Z., & Owens, A.
- Affiliations
- University of Michigan (US)
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 10491-10503
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386076652
- Cited by
- 101
- References
- 117
- Citations by year
- 2026: 35 · 2025: 39 · 2024: 20 · 2023: 7
- FWCI
- 10.80
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- U.S. Department of Defense
- Defense Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Mathematics › Statistics and Probability › Benford’s Law and Fraud Detection
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- video forensics, self-supervised learning, audio-video synchronization
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
