IP Library › Granted Patent US 12,412,376
Granted Patent B2
US 12,412,376 · App. 18/744,440 · Granted Sep 9, 2025

Machine-learning-based detection of fake videos

Inventors: Gaurav Bharaj (San Francisco, CA); Trevine Oorloff (College Park, MD); Surya Koppisetti (Coquitlam, CA); Nicolò Bonettini (Montefiorino, IT); Ben Colman (New York, NY); Ali Shahriyari (Las Vegas, NV)
Assignee: Reality Defender, Inc.
G06V10/774G06V20/41G06V20/49G06V40/172G06V40/40G10L17/02G10L17/04G10L17/26G10L25/57
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,412,376
App. No.
18/744,440
Granted
Sep 9, 2025
Kind
B2
Abstract

A method for training a model for classifying videos as real or fake can include generating image tiles and audio data segments from an input video, generating a sequence of image embeddings based on the image tiles using a visual encoder and a sequence of audio embeddings based on the audio data segments using an audio encoder, transforming, using a V2A network, a first subset of the sequence of image embeddings into synthetic audio embeddings, transforming, using an A2V network, a first subset of the sequence of audio embeddings into synthetic image embeddings, updating the sequence of image embeddings by using the synthetic image embeddings, updating the sequence of audio embeddings using the synthetic audio embeddings, training the encoders and the networks using the updated sequences of image embeddings and audio embeddings, and training a classifier using the trained encoders and the trained networks.

Claims (63)

1. A method for training a model comprising a visual encoder, an audio encoder, an audio-to-visual (A2V) network, a visual-to-audio (V2A) network, and a classifier for classifying videos as real or fake, the method comprising:

generating a sequence of image tiles from image data from an input video;

generating a plurality of data segments representing audio data from the input video;

generating a sequence of image embeddings based on the sequence of image tiles using the visual encoder;

generating a sequence of audio embeddings based on the sequence of data segments using the audio encoder;

transforming, using the V2A network, a first subset of the sequence of image embeddings into one or more synthetic audio embeddings, wherein the first subset of the sequence of image embeddings corresponds to a first set of time points in the input video;

transforming, using the A2V network, a first subset of the sequence of audio embeddings into one or more synthetic image embeddings, wherein the first subset of the sequence of audio embeddings corresponds to a second set of time points in the input video complementary to the first set of time points;

updating the sequence of image embeddings by replacing a second subset of the sequence of image embeddings with the one or more synthetic image embeddings, wherein the second subset of the sequence of image embeddings corresponds to the second set of time points;

updating the sequence of audio embeddings by replacing a second subset of the sequence of audio embeddings with the one or more synthetic audio embeddings, wherein the second subset of the sequence of audio embeddings corresponds to the first set of time points;

training the visual encoder, the audio encoder, the V2A network, and the A2V network based on the updated sequence of image embeddings and the updated sequence of audio embeddings;

training the classifier to classify videos as real or fake using the trained visual encoder, the trained audio encoder, the trained V2A network, and the trained A2V network, wherein the classifier is configured to receive image embeddings for the videos from the trained visual encoder, audio embeddings for the videos from the trained audio encoder, synthetic image embeddings for the videos from the trained A2V network, and synthetic audio embeddings for the videos from the trained V2A network.

2. The method of claim 1 , wherein:

the first subset of the sequence of image embeddings comprises half of the image embeddings, and

the first subset of the sequence of audio embeddings comprises half of the audio embeddings.

3. The method of claim 1 , wherein the first subset of the sequence of image embeddings and the first subset of the sequence of audio embeddings are randomly selected.

4. The method of claim 1 , wherein training the visual encoder, the audio encoder, the V2A network, and the A2V network based on the updated sequence of image embeddings and the updated sequence of audio embeddings comprises:

decoding the updated sequence of image embeddings to produce a reconstruction of the sequence of image tiles; and

decoding the updated sequence of audio embeddings to produce a reconstruction of the plurality of data segments.

5. The method of claim 4 , wherein the updated sequence of image embeddings is decoded using a visual decoder.

6. The method of claim 4 , wherein the updated sequence of audio embeddings is decoded using an audio decoder.

7. The method of claim 1 , wherein training the visual encoder, the audio encoder, the V2A network, and the A2V network based on the updated sequence of image embeddings and the updated sequence of audio embeddings further comprises computing a dual-objective loss, wherein a first objective of the dual-objective loss depends on the sequence of audio embeddings and the sequence of image embeddings and a second objective of the dual-objective loss depends on the sequence of image tiles, the plurality of data segments, the reconstruction of the sequence of image tiles, and the reconstruction of the plurality of data segments.

8. The method of claim 1 , wherein training the classifier to classify videos as real or fake using the trained visual encoder, the trained audio encoder, the trained V2A network, and the trained A2V network comprises:

generating a second sequence of image tiles from image data from a labeled training video comprising a label indicating whether the labeled training video is real or fake;

generating a second plurality of data segments representing audio data from the labeled training video;

generating a second sequence of image embeddings based on the second sequence of image tiles using the trained visual encoder;

generating a second sequence of audio embeddings based on the second sequence of data segments using the trained audio encoder;

transforming, using the trained V2A network, the second sequence of image embeddings into a sequence of synthetic audio embeddings;

transforming, using the trained A2V network, the second sequence of audio embeddings into a sequence synthetic image embeddings;

concatenating the second sequence of image embeddings and the sequence of synthetic image embeddings to produce a combined sequence of image embeddings;

concatenating the second sequence of audio embeddings and the sequence of synthetic audio embeddings to produce a combined sequence of audio embeddings; and

classifying the labeled training video as real or fake based on the combined sequence of audio embeddings and the combined sequence of image embeddings.

9. The method of claim 8 , wherein training the classifier to classify videos as real or fake using the trained visual encoder, the trained audio encoder, the trained V2A network, and the trained A2V network further comprises computing a cross-entropy loss objective using label indicating whether the labeled training video is real or fake.

10. The method of claim 1 , wherein the classifier comprises an audio mode patch reduction network, a visual mode patch reduction network, and a classifier head.

11. The method of claim 1 , wherein a number of image tiles in the sequence of image tiles and a number of data segments in the sequence of data segments are determined based on a sampling frequency of the image data, a sampling frequency of the audio data, and a time duration of the input video.

12. The method of claim 1 , further comprising:

providing the trained model with a second input video; and

classifying the second input video as real or fake using the trained model.

13. The method of claim 12 , wherein the second input video comprises real audio data and AI-generated image data.

14. The method of claim 12 , wherein the second input video comprises real image data and AI-generated audio data.

15. The method of claim 12 , wherein the second input video comprises AI-generated image data and AI-generated audio data.

16. The method of claim 1 , wherein the input video shows a human face.

17. A system for training a model comprising a visual encoder, an audio encoder, an audio-to-visual (A2V) network, a visual-to-audio (V2A) network, and a classifier for classifying videos as real or fake, the system comprising one or more processors configured to:

generate a sequence of image tiles from image data from an input video;

generate a plurality of data segments representing audio data from the input video;

generate a sequence of image embeddings based on the sequence of image tiles using the visual encoder;

generate a sequence of audio embeddings based on the sequence of data segments using the audio encoder;

transform, using the V2A network, a first subset of the sequence of image embeddings into one or more synthetic audio embeddings, wherein the first subset of the sequence of image embeddings corresponds to a first set of time points in the input video;

transform, using the A2V network, a first subset of the sequence of audio embeddings into one or more synthetic image embeddings, wherein the first subset of the sequence of audio embeddings corresponds to a second set of time points in the input video complementary to the first set of time points;

update the sequence of image embeddings by replacing a second subset of the sequence of image embeddings with the one or more synthetic image embeddings, wherein the second subset of the sequence of image embeddings corresponds to the second set of time points;

update the sequence of audio embeddings by replacing a second subset of the sequence of audio embeddings with the one or more synthetic audio embeddings, wherein the second subset of the sequence of audio embeddings corresponds to the first set of time points;

train the visual encoder, the audio encoder, the V2A network, and the A2V network based on the updated sequence of image embeddings and the updated sequence of audio embeddings;

train the classifier to classify videos as real or fake using the trained visual encoder, the trained audio encoder, the trained V2A network, and the trained A2V network, wherein the classifier is configured to receive image embeddings for the videos from the trained visual encoder, audio embeddings for the videos from the trained audio encoder, synthetic image embeddings for the videos from the trained A2V network, and synthetic audio embeddings for the videos from the trained V2A network.

18. A non-transitory computer readable storage medium storing instructions for training a model comprising a visual encoder, an audio encoder, an audio-to-visual (A2V) network, a visual-to-audio (V2A) network, and a classifier for classifying videos as real or fake that, when executed by one or more processors of a computer system, cause the computer system to:

generate a sequence of image tiles from image data from an input video;

generate a plurality of data segments representing audio data from the input video;

generate a sequence of image embeddings based on the sequence of image tiles using the visual encoder;

generate a sequence of audio embeddings based on the sequence of data segments using the audio encoder;

transform, using the V2A network, a first subset of the sequence of image embeddings into one or more synthetic audio embeddings, wherein the first subset of the sequence of image embeddings corresponds to a first set of time points in the input video;

transform, using the A2V network, a first subset of the sequence of audio embeddings into one or more synthetic image embeddings, wherein the first subset of the sequence of audio embeddings corresponds to a second set of time points in the input video complementary to the first set of time points;

update the sequence of image embeddings by replacing a second subset of the sequence of image embeddings with the one or more synthetic image embeddings, wherein the second subset of the sequence of image embeddings corresponds to the second set of time points;

update the sequence of audio embeddings by replacing a second subset of the sequence of audio embeddings with the one or more synthetic audio embeddings, wherein the second subset of the sequence of audio embeddings corresponds to the first set of time points;

train the visual encoder, the audio encoder, the V2A network, and the A2V network based on the updated sequence of image embeddings and the updated sequence of audio embeddings;

train the classifier to classify videos as real or fake using the trained visual encoder, the trained audio encoder, the trained V2A network, and the trained A2V network, wherein the classifier is configured to receive image embeddings for the videos from the trained visual encoder, audio embeddings for the videos from the trained audio encoder, synthetic image embeddings for the videos from the trained A2V network, and synthetic audio embeddings for the videos from the trained V2A network.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 12, 2024
From: BHARAJ, GAURAV; OORLOFF, TREVINE; KOPPISETTI, SURYA; BONETTINI, NICOLÒ; COLMAN, BEN; SHAHRIYARI, ALI
To: REALITY DEFENDER, INC.
Reel/Frame 069226/0703 →
Continuity (2)
Provisional Application 63600581 · Nov 17, 2023
Related Publication 20250166358A1 · May 22, 2025
References Cited (67)
US 20200160502A1 · Nießner · 2020 [cited by examiner]
US 20210174487A1 · Nießner · 2021 [cited by examiner]
US 20220138472A1 · Mittal · 2022 [cited by examiner]
US 20220310113A1 · Tzinis · 2022 [cited by examiner]
US 20220343543A1 · Sengupta · 2022 [cited by examiner]
US 20230401824A1 · Khan · 2023 [cited by examiner]
Gong, Yuan, et al. “Contrastive audio-visual masked autoencoder.” arXiv preprint arXiv:2210.07839 (2022). [cited by examiner]
Devlin, Jacob et al. “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.” North American Chapter of the Association for Computational Linguistics (2019). [cited by examiner]
Yang et al., “AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake,” in IEEE Transactions on Information Forensics and Security, vol. 18, pp. 2015-2029, 2023, doi: 10.1109/TIFS.2023.3262148. [cited by examiner]
Lewis, John et al. “Deepfake Video Detection Based on Spatial, Spectral, and Temporal Inconsistencies Using Multimodal Deep Learning.” 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) (2020): 1-9. [cited by examiner]
Taylor, W. L. (1953). “Cloze procedure”: a new tool for measuring readability. Journalism Quarterly, 30, 415-433. [cited by examiner]
Afouras et al. (Oct. 2018). “LRS3-TED: a large-scale dataset for visual speech recognition,” Visual Geometry Group, Department of Engineering Science, University of Oxford, UK; 2 pages. [cited by applicant]
Agarwal et al. “Detecting Deep-Fake Videos from Phoneme-Viseme Mismatches,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 13-19, 2020, Seattle, WA; 9 pages. [cited by applicant]
Arjovsky et al. “Wasserstein Generative Adversarial Networks,” 34th International Conference on Machine Learning, Aug. 6-11, 2017, Sydney, Australia; 10 pages. [cited by applicant]
Baltruaitis et al. (May 2017). “Multimodal Machine Learning: A Survey and Taxonomy,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2): pp. 1-20. [cited by applicant]
Cai et al. “MARLIN: Masked Autoencoder for facial video representation learnINg,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 17-24, 2023, Vancouver, BC, Canada; pp. 1493-1504. [cited by applicant]
Cheng et al. (Jun. 2022). “Voice-Face Homogeneity Tells Deepfake,” located at https://arxiv.org/abs/2203.02195; pp. 1-13. [cited by applicant]
Chugh et al. “Not made for each other—Audio-Visual Dissonance-based Deepfake Detection and Localization,” 28th ACM international Conference on multimedia, Oct. 12-16, 2020, Seattle, Washington; 9 pages. [cited by applicant]
Chung et al. (2016). “Out of time: automated lip sync in the wild,” Visual Geometry Group, Department of Engineering Science, University of Oxford; 14 pages. [cited by applicant]
Devlin et al. “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” 2019 North American Chapter of the Association for Computational Linguistics, Jun. 2-7, 2019, Minneapolis, Minnesota; pp.… [cited by applicant]
Dolhansky et al. (Oct. 2020). “The Deepfake Detection Challenge (DFDC) Dataset,” located at https://arxiv.org/abs/2006.07397; pp. 1-13. [cited by applicant]
Dong et al. “Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 18-22, 2023, Vancouver, BC, Canada… [cited by applicant]
Dong et al. “Protecting Celebrities from DeepFake with Identity Consistency Transformer,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 18-24, 2022. New Orleans, LA, pp. 9458-9468. [cited by applicant]
Dosovitskiy et al. “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” International Conference on Learning Representations, May 3-7, 2021, Virtual Conference; pp. 1-22. [cited by applicant]
Feng et al. “Self-Supervised Video Forensics by Audio-Visual Anomaly Detection,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 17-24, 2023, Vancouver, BC, Canada; pp. 10491-10503. [cited by applicant]
Gemmeke et al. “Audio Set: An Ontology and Human-Labeled Dataset for Audio Events,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar. 5-9, 2017; pp. 776-780. [cited by applicant]
Georgescu et al. “Audiovisual Masked Autoencoders,” IEEE/CVF International Conference on Computer Vision, Oct. 1-6, 2023, Paris, France; pp. 16144-16154. [cited by applicant]
Guzhov et al. “AudioCLIP: Extending CLIP to Image, Text and Audio,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 22-27, 2022, Singapore; pp. 1-14. [cited by applicant]
Haliassos et al. “Leveraging real talking faces via self-supervision for robust forgery detection,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 18-24, 2022. New Orleans, Louisiana, pp. 14950-149… [cited by applicant]
Haliassos et al. “Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 20-25, 2021. Nashville, Tennessee; pp. 5039-5… [cited by applicant]
He et al. “Masked Autoencoders Are Scalable Vision Learners,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 18-24, 2022, New Orleans, Louisiana; pp. 16000-16009. [cited by applicant]
Huang et al. “Masked Autoencoders that Listen,” 36th International Conference on Neural Information Processing Systems, Nov. 28-Dec. 9, 2022, New Orleans, Louisiana; pp. 1-20. [cited by applicant]
Huang et al. “Implicit Identity Driven Deepfake Face Swapping Detection,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 17-24, 2023, Vancouver, BC, Canada; pp. 4490-4499. [cited by applicant]
Huang et al. “MAViL: Masked Audio-Video Learners,” 37th Conference on Neural Information Processing Systems (NeurIPS 2023), Dec. 10-16, 2023, New Orleans, Louisiana; pp. 1-23. [cited by applicant]
Ilyas et al. (Feb. 2023). “AVFakeNet: A unified end-to-end Dense Swin Transformer deep learning model for audio-visual deepfakes detection,” Applied Soft Computing 136(110124); pp. 1-16. [cited by applicant]
International Search Report and Written Opinion mailed Dec. 17, 2024, directed to International Application No. PCT/US2024/056146; 12 pages. [cited by applicant]
Jia et al. “Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis,” 32nd Annual Conference on Neural Information Processing Systems (NIPS), Dec. 2-8, 2018, Montréal, Canada; pp. 1-11. [cited by applicant]
Jung et al. (Apr. 2020). “DeepVision: Deepfakes detection using human eye blinking pattern,” IEEE Access; pp. 1-13. [cited by applicant]
Kaddar et al. “HHCiT: Deepfake Video Detection Using a Hybrid Model of CNN features and Vision Transformer,” In 2021 International Conferenceon Visual Communications and Image Processing (VCIP), Dec. 5-8, 2021, Munich, … [cited by applicant]
Khalid et al. (Sep. 2021). “FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset,” located at https://arxiv.org/abs/2108.05080; pp. 1-22. [cited by applicant]
Korshunova et al. “Fast Face-swap Using Convolutional Neural Networks,” IEEE International Conference on Computer Vision (ICCV), Oct. 22-29, 2017, Venice, Italy; pp. 3677-3685. [cited by applicant]
Kwon et al. “KoDF: A Large-scale Korean DeepFake Detection Dataset,” IEEE/CVF International Conference on Computer Vision, Oct. 10-17, 2021, Montreal, QC, Canada; pp. 10744-10753. [cited by applicant]
Li et al. “In Ictu Oculi: Exposing Al Created Fake Videos by Detecting Eye Blinking,” IEEE International Workshop on Information Forensics and Security (WIFS), Dec. 10-13, 2018, Hong Kong, China; pp. 1-7. [cited by applicant]
Lutz et al. (Aug. 2021). “DeepFake Detection with Inconsistent Head Poses: Reproducibility and Analysis,” located at https://arxiv.org/abs/2108.12715; 10 pages. [cited by applicant]
Ma et al. “Pixel Codec Avatars,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 20-25, 2021, Nashville, Tennessee; pp. 64-73. [cited by applicant]
Mittal et al. “Emotions Don't Lie: An Audio-Visual Deepfake DetectionMethod using Affective Cues,” 28th ACM International Conference on Multimedia, Oct. 12-16, 2020, Seattle, Washington; 10 pages. [cited by applicant]
Morgado et al. “Robust Audio-Visual Instance Discrimination,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 20-25, 2021, Nashville, Tennessee; pp. 12934-12945. [cited by applicant]
Nirkin et al. “FSGAN: Subject Agnostic Face Swapping and Reenactment,” IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 27-Nov. 2, 2019, Seoul, Korea; pp. 7184-7193. [cited by applicant]
Ojha et al. “Towards Universal Fake Image Detectors thatGeneralize Across Generative Models,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 17-24, 2023, Vancouver, BC, Canada; pp. 24480-244… [cited by applicant]
Prajwal et al. “A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild,” 28th ACM International Conference on Multimedia, Oct. 12-16, 2020, Seattle, Washington; 10 pages. [cited by applicant]
Radford et al. “Learning Transferable Visual Models From Natural Language Supervision,” 38th International Conference on Machine Learning (ICML 2021), Jul. 18-24, 2021, Virtual Conference; 16 pages. [cited by applicant]
Rossler et al. “FaceForensics++: Learning to Detect Manipulated Facial Images,” IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Oct. 27-28, 2019, Seoul, Korea; pp. 1-11. [cited by applicant]
Rouditchenko et al. “AVLnet: Learning Audio-Visual Language Representations from Instructional Videos,” Annual Conference of the International Speech Communication Association, Aug. 30-Sep. 3, 2021, Brno, Czechia; pp. 1… [cited by applicant]
Tong et al. “VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training,” 36th Conference on Neural Information Processing Systems (NeurIPS 2022), Nov. 28-Dec. 9, 2022, New Orleans,… [cited by applicant]
Wang et al. “AltFreezing for More General Video Face Forgery Detection,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 17-24, 2023, Vancouver, BC, Canada; pp. 4129-4138. [cited by applicant]
Wang et al. “FaceX-Zoo: A PyTorch Toolbox for Face Recognition,” 29th ACM International Conference on Multimedia, Oct. 20-24, 2021, Chengdu, China; pp. 1-9. [cited by applicant]
Wang et al. “One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 20-25, 2021, Nashville, Tennessee; pp. 10039-10049. [cited by applicant]
Wodajo et al. (Feb. 2021) “Deepfake Video Detection Using Convolutional Vision Transformer,” located at https://arxiv.org/abs/2102.11126; pp. 1-9. [cited by applicant]
Wolf et al. “Face Recognition in Unconstrained Videos with Matched Background Similarity,” Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 20-25, 2011, Colorado Springs, Colorado; pp. 529-534. [cited by applicant]
Wu et al. (Jun. 2023). “Deepfake in the Metaverse: An Outlook Survey,” located at https://arxiv.org/abs/2306.07011; pp. 1-8. [cited by applicant]
Yang et al. “Exposing Deep Fakes Using Inconsistent Head Poses,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 12-17, 2019, Brighton, United Kingdom; 4 pages. [cited by applicant]
Zhao et al. “Exploring Complementarity of Global and Local Spatiotemporal Information for Fake Face Video Detection,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 22-27, 2022, S… [cited by applicant]
Zheng et al. “Exploring Temporal Coherence for More General Video Face Forgery Detection,” IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 10-17, 2021, Montreal, Canada; pp. 15044-15054. [cited by applicant]
Zhou et al. “Joint Audio-Visual Deepfake Detection,” IEEE/CVF International Conference on Computer Vision, Oct. 11-17, 2021, Montreal, BC, Canada; pp. 14800-14809. [cited by applicant]
Zhou et al. (Aug. 2018). “VisemeNet: Audio-Driven Animator-Centric Speech Animation,” ACM Transactions on Graphics (TOG), 37(4): 10 pages. [cited by applicant]
Zhu et al. “CelebV-HQ: A Large-Scale Video Facial Attributes Dataset,” European Conference on Computer Vision (ECCV 2022), Oct. 25-27, 2022, Tel Aviv, Israel; pp. 1-27. [cited by applicant]
Zhuang et al. “UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection,” European Conference on Computer Vision (ECCV 2022), Oct. 23-27, 2022, Tel Aviv, Israel; pp. 1-16. [cited by applicant]