Exposing Deep Fakes Using Inconsistent Head Poses
Open accessThe DOI matches its Crossref record; 20 of the 22 references it cites were found in a registry or an index.
Abstract
In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes). Our method is based on the observations that Deep Fakes are created by splicing synthesized face region into the original image, and in doing so, introducing errors that can be revealed when 3D head poses are estimated from the face images. We perform experiments to demonstrate this phenomenon and further develop a classification method based on this cue. Using features based on this cue, an SVM classifier is evaluated using a set of real face images and Deep Fakes.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Visual modality datasets dominate with over 20 publicly available resources [29, 30, 30-44], while audio modality datasets are fewer, with 11 notable datasets [45-55].”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [34]
In the citing paper
“Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data.”
From Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection (2024) · cites this paper as [57]
In the citing paper
“UADFV is used in research to develop deepfake detection methods and improve the robustness of existing methods (Yang etal. 2019).”
From Deepfake video detection: challenges and opportunities (2024) · cites this paper as Yang et al. 2019
In the citing paper
“Existing low-level approaches concentrate on inconsistent behaviors, including eye blinking [14], facial expression, head movement [15, 16], lip movement [27, 28], gestural mannerisms [29], and misalignment between the eyes [21].”
From Attention-based Multimodal learning framework for Generalized Audio-Visual Deepfake Detection (2023) · cites this paper as [15]
In the citing paper
“UADFV [136] dataset includes 98 videos, totaling 32,752 frames, evenly split between 49 real videos and 49 fake ones.”
From Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions (2023) · cites this paper as [136]
Citations
Cites
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017) · arXiv · doi:10.48550/arxiv.1710.10196 · Cited by 4,727
Dlib-ml: A Machine Learning Toolkit
King, D. E. (2009) · doi:10.5555/1577069.1755843 · Cited by 2,777
MesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872
Openface 2.0: facial behavior analysis toolkit
Baltrusaitis, T., Zadeh, A., Lim, Y. C., & Morency, L.-P. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00019 · Cited by 1,861
Face2Face: Real-Time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Niessner, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.262 · Cited by 1,747
Deepfake Video Detection Using Recurrent Neural Networks
Guera, D., & Delp, E. J. (2018) · 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2018.8639163 · Cited by 1,285
In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking
Li, Y., Chang, M.-C., & Lyu, S. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630787 · Cited by 1,089
Self-citationDeep Fakes: A Looming Challenge for Privacy, Democracy, and National Security
Chesney, R., & Citron, D. K. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3213954 · Cited by 880 · cited 1×
“Together with other forms of misinformation shared through the digital social network, Deep Fakes created digital impersonations have become a serious problem with negative social impacts [8].”
BackgroundDemo of Face2Face: real-time face capture and reenactment of RGB videos
Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., & Nießner, M. (2016) · ACM SIGGRAPH 2016 Emerging Technologies · doi:10.1145/2929464.2929475 · Cited by 589
Cited by
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846
“To date, we have the UADFV dataset [53], the DeepFake-TIMIT dataset (DF-TIMIT) [25], the FaceForenscics++ dataset (FF-DF) [40]2, the Google DeepFake detection dataset (DFD) [15], and the FaceBook DeepFake detection challenge (DFDC) dataset [14].”
MethodInfluentialSelf-citationDeepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237
Multi-attentional Deepfake Detection
Zhao, H., Wei, T., Zhou, W., Zhang, W., Chen, D., & Yu, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00222 · Cited by 1,019
“Early works [46, 23] detect the forgery through visual biological artifacts, e.”
BackgroundMedia Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979
The Creation and Detection of Deepfakes: A Survey
Mirsky, Y., & Lee, W. (2022) · ACM Computing Surveys · doi:10.1145/3425780 · Cited by 863
Metadata
- Authors
- Yang, X., Li, Y., & Lyu, S.
- Affiliations
- University at Albany, State University of New York (US)
- Venue
- ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2019-05
- Pages
- 8261-8265
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2963684180
- Cited by
- 1,196
- References
- 22
- Citations by year
- 2026: 103 · 2025: 208 · 2024: 188 · 2023: 180 · 2022: 194 · 2021: 186 · 2020: 122 · 2019: 14
- FWCI
- 42.06
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- deepfakes, face forgery detection, head pose estimation, image forgery detection, video forgery detection, support vector machine classification
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: Exposing Deep Fakes Using Inconsistent Head Poses. https://app.cochat.ai/papers/10.1109/icassp.2019.8683164
- The paper
- Yang, X., Li, Y., & Lyu, S. (2019). Exposing Deep Fakes Using Inconsistent Head Poses. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2019.8683164
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.