Deepfake Video Detection through Optical Flow Based CNN
Open accessAbstract
Recent advances in visual media technology have led to new tools for processing and, above all, generating multimedia contents. In particular, modern AI-based technologies have provided easy-to-use tools to create extremely realistic manipulated videos. Such synthetic videos, named Deep Fakes, may constitute a serious threat to attack the reputation of public subjects or to address the general opinion on a certain event. According to this, being able to individuate this kind of fake information becomes fundamental. In this work, a new forensic technique able to discern between fake and original video sequences is given; unlike other state-of-the-art methods which resorts at single video frames, we propose the adoption of optical flow fields to exploit possible inter-frame dissimilarities. Such a clue is then used as feature to be learned by CNN classifiers. Preliminary results obtained on FaceForensics++ dataset highlight very promising performances.
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
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 recent common underlying mechanism for deepfake creation is deep learning models such as autoencoders and generative adversarial networks (GANs).
“the re- cent common underlying mechanism for deepfake cre- ation is deep learning models such as autoencoders and generative adversarial networks (GANs)”
From Deep learning for deepfakes creation and detection: A survey (2022) · cites this paper as [7]
The Introduction says deep learning advances the creation of multimedia content and describes techniques for generating synthetic videos. The References include StarGAN, but our copy does not identify autoencoders and GANs as the common underlying mechanisms of deepfake creation. (LLM, conf=0.82)
Experimental — accuracy not yet measuredAmerini et al. (2019) used CNN with optical flow to differentiate between fake and real videos.
“Amerini etal. (2019) have used CNN with optical flow to differentiate between fake and real videos.”
From Deepfake video detection: challenges and opportunities (2024) · cites this paper as Amerini et al. 2019
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation
Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., & Choo, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00916 · Cited by 4,163 · see citing works
FaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · see citing works
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Sun, D., Yang, X., Liu, M.-Y., & Kautz, J. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00931 · Cited by 2,727 · see citing works
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 · see citing works
The computation of optical flow
Beauchemin, S. S., & Barron, J. A. (1995) · ACM Computing Surveys · doi:10.1145/212094.212141 · Cited by 1,282 · see citing works
Kim, H., Garrido, P., Tewari, A., Xu, W., Thies, J., Nießner, M., Pérez, P., Richardt, C., Zollhöfer, M., & Theobalt, C. (2018) · ACM Transactions on Graphics · doi:10.1145/3197517.3201283 · Cited by 692 · see citing works
Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., & Nießner, M. (2016) · ACM SIGGRAPH Emerging Technologies · doi:10.1145/2929464.2929475 · Cited by 585 · see citing works
Recurrent convolutional strategies for face manipulation detection in videos
Sabir, E., Cheng, J., Jaiswal, A., AbdAlmageed, W., Masi, I., & Natarajan, P. (2019) · arXiv · doi:10.48550/arxiv.1905.00582 · Cited by 443 · see citing works
(2019) · Cited by 415 · see citing works
FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
Rössler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nießner, M. (2018) · arXiv · doi:10.48550/arxiv.1803.09179 · Cited by 339 · see citing works
In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye BlinkingPreprint
Li, Y., Chang, M., & Lyu, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.02877 · Cited by 176 · see citing works
Regularization of optic flow estimates by means of weighted vector median filtering
Alparone, L., Barni, M., Bartolini, F., et al. (1999) · IEEE Transactions on Image Processing · doi:10.1109/83.791974 · Cited by 27 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Deepfakes 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 · see citing works
“Finally, in [101], Amerini et al. proposed the adoption of optical flow fields to exploit possible inter-frame dissimilarities.”
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 · see citing works
“[190] the optical flow field is estimated to exploit discrepancies in motion across frames, but only some preliminary results are presented.”
BackgroundThinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues
Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58610-2_6 · Cited by 1,058 · see citing works
“Following previous face forgery detection methods [51,19,40,5], we conduct our experiments on the challenging FaceForensics++ [50] dataset.”
BackgroundMethodThe Creation and Detection of Deepfakes: A Survey
Mirsky, Y., & Lee, W. (2020) · arXiv · doi:10.48550/arxiv.2004.11138 · Cited by 863
The Creation and Detection of Deepfakes: A Survey
Mirsky, Y., & Lee, W. (2022) · ACM Computing Surveys · doi:10.1145/3425780 · Cited by 863 · see citing works
“In [25] a classier is trained pairs of sequential frames and in [11] the authors rene the network’s focus by monitoring the frames’ optical ow.”
Deepfake Detection: A Systematic Literature Review
Rana, M. S., Nobi, M. N., Murali, B., & Sung, A. H. (2022) · IEEE Access · doi:10.1109/access.2022.3154404 · Cited by 573 · see citing works
Generalizing Face Forgery Detection with High-frequency Features
Luo, Y., Zhang, Y., Yan, J., & Liu, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01605 · Cited by 609 · see citing works
“[29, 34, 55, 9, 7, 32] targeted at specific artifacts such as abnormal eye-blinking frequency [29] or head-pose inconsistency [55].”
BackgroundMethodMasood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543 · see citing works
“This method [156] exhibits better deepfake detection performance, however, only initial results have been reported.”
BackgroundInfluentialDetecting Deepfakes with Self-Blended Images
Shiohara, K., & Yamasaki, T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01816 · Cited by 503 · see citing works
“, head pose [62], eye blinking [30, 40], mouth movements [27], neuron behaviors [60], optical flow [9], and steganalysis features [24]).”
BackgroundDeep Learning for Deepfakes Creation and Detection: A Survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2019) · arXiv · doi:10.48550/arxiv.1909.11573 · Cited by 464
Deep learning for deepfakes creation and detection: A survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103525 · Cited by 464 · see citing works
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
Chen, L., Zhang, Y., Song, Y., Liu, L., & Wang, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01815 · Cited by 307 · see citing works
“Recent studies have made various attempts for deepfake detection and achieve remarkable success [26, 41, 3, 2, 32, 39, 14, 24, 30, 29, 19, 47, 23, 36, 5].”
BackgroundExploring Temporal Coherence for More General Video Face Forgery Detection
Zheng, Y., Bao, J., Chen, D., Zeng, M., & Wen, F. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01477 · Cited by 320 · see citing works
Combining EfficientNet and Vision Transformers for Video Deepfake Detection
Coccomini, D. A., Messina, N., Gennaro, C., & Falchi, F. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-06433-3_19 · Cited by 296 · see citing works
“Some efforts to capture spatio-temporal inconsistencies were made in [26] using 3DCNN networks and in [3], which presented a method that exploits optical flow to detect video glitches.”
MethodCIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images
Bird, J. J., & Lotfi, A. (2024) · IEEE Access · doi:10.1109/access.2024.3356122 · Cited by 308 · see citing works
“When discussing the topic of vision, the results in [18] suggest that optical flow techniques could detect synthetic human faces within the FaceForensics dataset with around 81.61% accuracy.”
BackgroundInfluentialA Survey on Deepfake Video Detection
Yu, P., Xia, Z., Fei, J., & Lu, Y. (2021) · IET Biometrics · doi:10.1049/bme2.12031 · Cited by 253 · see citing works
“Some preprocessing methods, such as optical flow calculation [33], had been proved to be useful to exploit interframe dissimilarities in network‐based methods.”
MethodUCF: Uncovering Common Features for Generalizable Deepfake Detection
Yan, Z., Zhang, Y., Fan, Y., & Wu, B. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02048 · Cited by 241 · see citing works
“Other notable directions are focusing on some specific representations, i.e., forgery region location [33], neuron behaviors [49], optical flow [4], landmark geometric features [42], 3D decomposition [59], erasing technology [47], and attentional networks [10, 55, 48].”
BackgroundDeepfake video detection: challenges and opportunities
Kaur, A., Noori Hoshyar, A., Saikrishna, V., Firmin, S., & Xia, F. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10810-6 · Cited by 214 · see citing works
“Amerini et al. (2019) have used CNN with optical flow to differentiate between fake and real videos.”
Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples
Hussain, S., Neekhara, P., Jere, M., Koushanfar, F., & McAuley, J. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00339 · Cited by 204 · see citing works
“02] Translation dx ⇠ U [ 20, 20], dy ⇠ U [ 20, 20] Down-sizing & Up-sizing Scaling factor r ⇠ U [2, 5]”
BackgroundAn improved dense cnn architecture for deepfake image detection
Patel, Y., Tanwar, S., Bhattacharya, P., Gupta, R., Alsuwian, T., Davidson, I. E., & Mazibuko, T. F. (2023) · IEEE Access · doi:10.1109/access.2023.3251417 · Cited by 196 · see citing works
“Guera et al. [27] proposed a recurrent neural network (RNN) model, and Amerini et al. [33] used CNN with the concept of using discrepancies across frames to identify DF videos.”
MethodCountering Malicious DeepFakes: Survey, Battleground, and Horizon
Juefei-Xu, F., Wang, R., Huang, Y., Guo, Q., Ma, L., & Liu, Y. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01606-8 · Cited by 191 · see citing works
“…CNN (Dang et al., 2019; Marra et al., 2020; Coz-zolino et al., 2018), CNN with local features (Tarasiou and Zafeiriou, 2020), CNN with optical flow (Amerini et al., 2019), ensembled CNNs (Bonettini et al., 2021b; Tariq et al., 2018), light-weight CNN (Sambhu and Canavan, 2020), 3D CNNs…”
MethodMTD-Net: Learning to Detect Deepfakes Images by Multi-Scale Texture Difference
Yang, J., Li, A., Xiao, S., Lu, W., & Gao, X. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3102487 · Cited by 184 · see citing works
Deepfake generation and detection: Case study and challenges
Patel, Y., Tanwar, S., Gupta, R., Bhattacharya, P., Davidson, I. E., Nyameko, R., Aluvala, S., & Vimal, V. (2023) · IEEE Access · doi:10.1109/access.2023.3342107 · Cited by 186 · see citing works
Deepfake generation and detection, a survey
Zhang, T. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11733-y · Cited by 176 · see citing works
“In [7], CNN classifiers are used to learn inter-frame dissimilarities.”
MethodFAMM: Facial Muscle Motions for Detecting Compressed Deepfake Videos Over Social Networks
Liao, X., Wang, Y., Wang, T., Hu, J., & Wu, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3278310 · Cited by 169 · see citing works
“The optical flow field was adopted to detect Deepfake videos [21].”
MethodTranscending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection
Yan, Z., Luo, Y., Lyu, S., Liu, Q., & Wu, B. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00858 · Cited by 166 · see citing works
“On the other hand, recent works of detecting video forgery focus on the temporal inconsistency [19, 53, 61], eye blinking [30], landmark geometric features [44], neuron behaviors [51], optical flow [2].”
BackgroundZhou, T., Wang, W., Liang, Z., & Shen, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00572 · Cited by 156 · see citing works
“, Xception [16], I3D [12]), and address image- [3, 80, 63, 75, 57, 68] or video-level [31, 6, 71, 37, 53] forgery classification.”
A comprehensive overview of Deepfake: generation, detection, datasets, and opportunities
Seow, J. W., Lim, M. K., Phan, R. C. W., & Liu, J. K. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.135 · Cited by 149 · see citing works
KoDF: A Large-scale Korean DeepFake Detection Dataset
Kwon, P., You, J., Nam, G., Park, S., & Chae, G. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01057 · Cited by 145 · see citing works
A Hybrid CNN-LSTM model for Video Deepfake Detection by Leveraging Optical Flow Features
Saikia, P., Dholaria, D., Yadav, P., Patel, V., & Roy, M. (2022) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892905 · Cited by 133 · see citing works
“One study on the effect of optical flow and CNN training was also discussed in the work [20].”
BackgroundMethodA Comprehensive Review of Deep-Learning-Based Methods for Image Forensics
Camacho, I. C., & Wang, K. (2021) · Journal of Imaging · doi:10.3390/jimaging7040069 · Cited by 133 · see citing works
A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats
Mubarak, R., Alsboui, T., Alshaikh, O., Inuwa-Dutse, I., Khan, S., & Parkinson, S. (2023) · IEEE Access · doi:10.1109/access.2023.3344653 · Cited by 132 · see citing works
“Amerini et al. [153] proposed a deepfake detection technique that employs the difference in optical flow fields to distinguish between genuine and manipulated videos.”
BackgroundAltFreezing for More General Video Face Forgery Detection
Wang, Z., Bao, J., Zhou, W., Wang, W., & Li, H. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00402 · Cited by 137 · see citing works
DeepFake detection algorithm based on improved vision transformer
Heo, Y.-J., Yeo, W.-H., & Kim, B. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03867-9 · Cited by 127 · see citing works
“Amerini [27] used Face2Face, which achieved an 81.61% of accuracy on 120 testing datasets [28].”
MethodInfluentialOptical Flow based CNN for detection of unlearnt deepfake manipulations
Caldelli, R., Galteri, L., Amerini, I., & Del Bimbo, A. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.03.005 · Cited by 115 · see citing works
Self-citationContraGAN: Contrastive Learning for Conditional Image GenerationPreprint
Kang, M., & Park, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.12681 · Cited by 115 · see citing works
Adversarial Threats to DeepFake Detection: A Practical Perspective
Neekhara, P., Dolhansky, B., Bitton, J., & Ferrer, C. C. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00103 · Cited by 117 · see citing works
“com/c/deepfake-detection-challenge ral Networks [1, 2, 19, 32, 34] to distinguish AI-generated fake videos from real videos.”
BackgroundInfluentialComparison of Deepfake Detection Techniques through Deep Learning
Taeb, M., & Chi, H. (2022) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp2010007 · Cited by 118 · see citing works
“VGG-19, even though it was great in terms of performance, aligns with results from [60]; it was computationally very expensive, especially if fed with augmented data.”
BackgroundA Multimodal Misinformation Detector for COVID-19 Short Videos on TikTok
Shang, L., Kou, Z., Zhang, Y., & Wang, D. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671928 · Cited by 107 · see citing works
Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes
Trinh, L., Tsang, M., Rambhatla, S., & Liu, Y. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00202 · Cited by 115 · see citing works
“Most forgery detection methods process deepfake videos frame-by-frame, and few explore multi-modal and temporal dynamics [74, 4].”
BackgroundDeepfakes generation and detection: a short survey
Akhtar, Z. (2023) · Journal of Imaging · doi:10.3390/jimaging9010018 · Cited by 106 · see citing works
“Face reenactment detection methods were designed by Cozzolino et al. [88] using CNNs; Matern et al. [89] using visual features with logistic regression and MLP; Rossler et al. [90] using mesoscopic, steganalysis, and CNN features; Sabir et al. [91] using RNN; Amerini et al. [65] using Optical Flow + CNNs; Kumar et al.…”
MethodInfluentialDeepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113 · see citing works
“Early forgery detection methods primarily depend on handcrafted features such as facial landmarks [27,132,133], optical flow [134], and various digital image processing techniques designed to enhance the visibility of artifacts [135].”
Self-citationDeepfake Detection: A Comprehensive Survey from the Reliability Perspective
Wang, T., Liao, X., Chow, K. P., Lin, X., & Wang, Y. (2025) · ACM Computing Surveys · doi:10.1145/3699710 · Cited by 107 · see citing works
“Moreover, heatmaps of the real faces are displayed in like manners, which are indistinguishable from that of the fake ones.”
Testing human ability to detect ‘deepfake’ images of human faces
Bray, S. D., Johnson, S. D., & Kleinberg, B. (2023) · Journal of Cybersecurity · doi:10.1093/cybsec/tyad011 · Cited by 96 · see citing works
Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors
Khalid, H., Kim, M., Tariq, S., & Woo, S. S. (2021) · Proceedings of the 1st Workshop on Synthetic Multimedia - Audiovisual Deepfake Generation and Detection · doi:10.1145/3476099.3484315 · Cited by 110 · see citing works
“The FF++ and DFDC datasets were used more often in most of the deepfake detection methods [2, 3, 27, 46, 61].”
MethodDeep Fake Video Detection Using Transfer Learning Approach
Suratkar, S. S., & Kazi, F. (2022) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-022-07321-3 · Cited by 97 · see citing works
Ganguly, S., Ganguly, A., Mohiuddin, S., Malakar, S., & Sarkar, R. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118423 · Cited by 101 · see citing works
Artifacts-Disentangled Adversarial Learning for Deepfake Detection
Li, X., Ni, R., Yang, P., Fu, Z., & Zhao, Y. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3217950 · Cited by 94 · see citing works
“Some works [10], [11] has extracted features from the spatial domain for classification and achieved excellent performance on specific datasets.”
BackgroundMethodA Robust Approach to Multimodal Deepfake Detection
Salvi, D., Liu, H., Mandelli, S., Bestagini, P., Zhou, W., Zhang, W., & Tubaro, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9060122 · Cited by 96 · see citing works
“Early forgery detection methods primarily depend on handcrafted features such as facial landmarks [12–14], optical flow [15] and various digital image processing techniques designed to enhance the visibility of artifacts [16].”
Kim, B., Xiong, A., Lee, D., & Han, K. (2021) · PLoS ONE · doi:10.1371/journal.pone.0260080 · Cited by 100 · see citing works
Lagrange Motion Analysis and View Embeddings for Improved Gait Recognition
Chai, T., Li, A., Zhang, S., Li, Z., & Wang, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01961 · Cited by 91 · see citing works
“Optical flow has been used in many areas including action recognition [3,26] and video generation [1].”
MethodDynamic Difference Learning With Spatio–Temporal Correlation for Deepfake Video Detection
Yin, Q., Lu, W., Li, B., & Huang, J. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3290752 · Cited by 92 · see citing works
“correlations, optical flow [37] was introduced to expose the motion differences between multiple frames to detect deepfake videos.”
MethodA review of deep learning‐based approaches for deepfake content detection
(2024) · doi:10.1111/exsy.13570 · Cited by 116 · see citing works
“(Amerini et al., 2019) presented a deepfake detection approach using optical flow vectors, calculated from two consecutive frames using a CNN-based method.”
MethodDetecting fake images by identifying potential texture difference
Yang, J., Xiao, S., Li, A., Lan, G., & Wang, H. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.06.043 · Cited by 86 · see citing works
A Comprehensive Survey on Passive Techniques for Digital Video Forgery Detection
Shelke, N. A., & Kasana, S. S. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09974-4 · Cited by 87 · see citing works
DFFMD: A Deepfake Face Mask Dataset for Infectious Disease Era With Deepfake Detection Algorithms
Alnaim, N. M., Almutairi, Z. M., Alsuwat, M. S., Alalawi, H. H., Alshobaili, A., & Alenezi, F. S. (2023) · IEEE Access · doi:10.1109/access.2023.3246661 · Cited by 91 · see citing works
“Amerini et al. [27] provided a novel forensic strategy for distinguishing between false and authentic video sequences, unlike existing state-of-the-art techniques that rely on single video frames.”
BackgroundEstimating optical flow: A comprehensive review of the state of the art
Alfarano, A., Maiano, L., Papa, L., & Amerini, I. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104160 · Cited by 78 · see citing works
Self-citationMRE-Net: Multi-Rate Excitation Network for Deepfake Video Detection
Pang, G., Zhang, B., Teng, Z., Qi, Z., & Jianping Fan, B. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3239607 · Cited by 79 · see citing works
“Many researchers invest their efforts to explore the temporal modeling strategies on deepfake video detection tasks, such as optical flow ([22], [23]), “2D CNN + LSTM”-like ([24], [25], [26]), 3D CNN ([27], [28], [29]), etc.”
BackgroundMethodOn the Robustness of Face Recognition Algorithms Against Attacks and Bias
Singh, R., Agarwal, A., Singh, M., Nagpal, S., & Mayank Vatsa, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i09.7085 · Cited by 14 · see citing works
“Moreover, the rise in Deep-Fakes (Amerini et al. 2019; Li and Lyu 2019) and other sophisticated morphing techniques demands robust solutions for detection of fake content.”
Detection of Deepfake Videos Using Long-Distance Attention
Lu, W., Liu, L., Zhang, B., Luo, J., Zhao, X., Zhou, Y., & Huang, J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3233063 · Cited by 75 · see citing works
“The optical flows and the movement patterns of the real face and fake face are classified in [20] and [21], respectively.”
BackgroundA literature review and perspectives in deepfakes: generation, detection, and applications
Dagar, D., & Vishwakarma, D. K. (2022) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-022-00241-w · Cited by 72 · see citing works
Deepfake forensics analysis: An explainable hierarchical ensemble of weakly supervised models
Silva, S. H., Bethany, M., Votto, A. M., Scarff, I. H., Beebe, N., & Najafirad, P. (2022) · Forensic Science International: Synergy · doi:10.1016/j.fsisyn.2022.100217 · Cited by 66 · see citing works
“[16] improve the network ’ s attention by evaluating the optical flow.”
BackgroundMethodDeepFake on Face and Expression Swap: A Review
Waseem, S., Abu Bakar, S. A. R. S., Ahmed, B. A., Omar, Z., Eisa, T. A. E., & Dalam, M. E. E. (2023) · IEEE Access · doi:10.1109/access.2023.3324403 · Cited by 65 · see citing works
An Experimental Evaluation on Deepfake Detection using Deep Face Recognition
Ramachandran, S., Nadimpalli, A. V., & Rattani, A. (2021) · IEEE International Carnahan Conference on Security Technology (ICCST) · doi:10.1109/iccst49569.2021.9717407 · Cited by 71 · see citing works
A Hybrid CNN-LSTM Approach for Precision Deepfake Image Detection Based on Transfer Learning
Al-Dulaimi, O. A. H. H., & Kurnaz, S. (2024) · Electronics · doi:10.3390/electronics13091662 · Cited by 64 · see citing works
“The authors in [47] proposed a novel forensic technique to distinguish between fake and real video sequences by utilizing optical flow fields to detect frame disparities.”
BackgroundA video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes
Wang, Y., & Dantcheva, A. (2020) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg47880.2020.00089 · Cited by 60 · see citing works
“Towards thwarting such adversarial attacks, early multimedia forensics based detection strategies have been proposed [9], [10], [11], [12].”
BackgroundAugmented Multi-Scale Spatiotemporal Inconsistency Magnifier for Generalized DeepFake Detection
Yu, Y., Zhao, X., Ni, R., Yang, S., Zhao, Y., & Kot, A. C. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3237322 · Cited by 63 · see citing works
“Early works directly adopt 3D CNN [16], [17], [48], RNN [12], [13], optical flow [49] or LSTM [14], [15] to extract the temporal clues for DeepFake detection.”
MethodDFGNN: An interpretable and generalized graph neural network for deepfakes detection
Khalid, F., Javed, A., Ain, Q., Ilyas, H., & Irtaza, A. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119843 · Cited by 58 · see citing works
Video deepfake detection using a hybrid CNN-LSTM-Transformer model for identity verification
Πετμεζάς, Γ., Vanian, V., Konstantoudakis, K., Almaloglou, E. E. I., & Zarpalas, D. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20548-6 · Cited by 67 · see citing works
“On the other hand, a study by Amerini et al. [31] proposed the use of optical flow fields as input to two semi-trained models, namely VGG16 and ResNet-50, to detect deepfake videos by exploiting possible inter-frame dissimilarities.”
Ramadhani, K. N., Munir, R., & Utama, N. P. (2024) · IEEE Access · doi:10.1109/access.2024.3352890 · Cited by 57 · see citing works
“In addition to RNN and motion tracking, Optical Flow method has been used in deepfake video detection research with CNN as the classification algorithm [10].”
MethodDeepfake Video Detection Based on MesoNet with Preprocessing Module
Xia, Z., Qiao, T., Xu, M., Wu, X., Han, L., & Chen, Y. (2022) · Symmetry · doi:10.3390/sym14050939 · Cited by 56 · see citing works
Al-Dhabi, Y., & Zhang, S. (2021) · IEEE International Conference on Computer Science, Artificial Intelligence and Electronic Engineering (CSAIEE) · doi:10.1109/csaiee54046.2021.9543264 · Cited by 55 · see citing works
Exploiting Complementary Dynamic Incoherence for DeepFake Video Detection
Wang, H., Liu, Z., & Wang, S. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3238517 · Cited by 57 · see citing works
Deepfake attribution: On the source identification of artificially generated images
Khoo, B., Phan, R. C. ‐., & Lim, C. H. (2021) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1438 · Cited by 56 · see citing works
“Classification algorithms for detecting deepfake videos exploit the frame-by-frame synthesis process of such videos that typically fail to enforce temporally coherent relationships between feature representations in consecutive frames (Amerini et al., 2019; Sabir et al., 2019).”
BackgroundA systematic literature review on deepfake detection techniques
Sharma, V. K., Garg, R. K., & Caudron, Q. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19906-1 · Cited by 61 · see citing works
MSVT: Multiple Spatiotemporal Views Transformer for DeepFake Video Detection
Yu, Y., Ni, R., Zhao, Y., Yang, S., Xia, F., Jiang, N., & Zhao, G. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3281448 · Cited by 56 · see citing works
Dynamic texture analysis for detecting fake faces in video sequences
Bonomi, M., Pasquini, C., & Boato, G. (2021) · Institutional Research Information System (Università degli Studi di Trento) · doi:10.1016/j.jvcir.2021.103239 · Cited by 51 · see citing works
“In in [5], a CNN is used to estimate and analyze the optical flow field across frames.”
MethodForensic Symmetry for DeepFakes
Li, G., Zhao, X., & Cao, Y. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3235579 · Cited by 50 · see citing works
“Amerini et al. [28] exploited optical flow field dissimilarities to discriminate original and DeepFake videos.”
BackgroundMCS-GAN: A Different Understanding for Generalization of Deep Forgery Detection
Xiao, S., Lan, G., Yang, J., Lu, W. B., Meng, Q., & Gao, X. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3279993 · Cited by 51 · see citing works
“Amerini et al. proposed the concept of the visual flow vector field, where the change vector information is extracted from consecutive frames and input into a VGG-16-based network for classification [31].”
BackgroundResNet-Swish-Dense54: a deep learning approach for deepfakes detection
Nawaz, M., Javed, A., & Irtaza, A. (2022) · The Visual Computer · doi:10.1007/s00371-022-02732-7 · Cited by 49 · see citing works
“Moreover, for the FaceForensic++ dataset, we have presented the comparison of the proposed approach with other DL models like XceptionNet [44], Vgg16 [62], ResNet34 [63], InceptionV3 [64], and attained results are given in Fig.”
MethodSeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes
Larue, N., Vu, N., Štruc, V., Peer, P., & Christophides, V. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01921 · Cited by 51 · see citing works
“Early detectors, e.g., [1, 3, 11, 27, 46], relied mostly on the known deficiencies of deepfake-generation techniques and focused on the detection of the corresponding visual artifacts.”
BackgroundDeepfake Detection Using Spatiotemporal Transformer
Kaddar, B., Fezza, S. A., Akhtar, Z., Hamidouche, W., Hadid, A., & Serra-Sagrista, J. S. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3643030 · Cited by 50 · see citing works
“In [6], the authors refined the network’s focus by monitoring the frames’ optical flow.”
Visual attention-based deepfake video forgery detection
Ganguly, S., Mohiuddin, S., Malakar, S., Cuevas, E., & Sarkar, R. (2022) · Pattern Analysis and Applications · doi:10.1007/s10044-022-01083-2 · Cited by 45 · see citing works
“The unnatural motion of facial components is brought into notice by Amer-ini et al. [26] where a CNN-based model PWC-Net [27] is used to extract optical flow matrices from the face images and then feed these into VGG16 [28]-based semi-trainable model to filter out authentic videos.”
MethodWhich Is Plagiarism: Fashion Image Retrieval Based on Regional Representation for Design Protection
Lang, Y., He, Y., Yang, F., et al. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00267 · Cited by 45 · see citing works
“Besides, the task is aimed to retrieve the plagiarized clothes with regional manipulation, which to some extent has a similar idea with Deepfake detection tasks [7, 15].”
MethodMotion Magnified 3-D Residual-in-Dense Network for DeepFake Detection
Mehra, A., Agarwal, A., Mayank Vatsa, A., & Singh, R. (2022) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2022.3201887 · Cited by 46 · see citing works
“In an attempt to highlight and capture these temporal cues better, Armerini et al. [6] employed optical flows to help capture the inter-frame dissimilarities.”
BackgroundDeepfake Detection Scheme Based on Vision Transformer and DistillationPreprint
Heo, Y. J., Choi, Y. J., Lee, Y., & Kim, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.01353 · Cited by 76 · see citing works
“As the method of optical flow based cnn, Amerini proposed a optical flow field to exploit possible inter-frame dissimilarities [4].”
MethodDeepfake detection via inter-frame inconsistency recomposition and enhancement
Zhu, C., Zhang, B., Yin, Q., Yin, C., & Lu, W. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110077 · Cited by 44 · see citing works
A Comparative Study of Deepfake Video Detection Method
Ramadhani, K. N., & Munir, R. (2020) · 2020 3rd International Conference on Information and Communications Technology (ICOIACT) · doi:10.1109/icoiact50329.2020.9331963 · Cited by 42 · see citing works
“Amerini et al. [8] using a Convolutional Neural Network (CNN) with Optical Flow feature.”
MethodHynek, N., Gavurová, B., & Kubák, M. (2025) · Journal of Innovation & Knowledge · doi:10.1016/j.jik.2025.100782 · Cited by 44 · see citing works
Leveraging edges and optical flow on faces for deepfake detection
Chintha, A., Rao, A. G., Sohrawardi, S. J., Bhatt, K., Wright, M., & Ptucha, R. (2020) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304936 · Cited by 43 · see citing works
“• Additive Gaussian Noise – μ = 0 and σ [1, 5].”
BackgroundFace Forgery Detection by 3D Decomposition and Composition Search
Zhu, X., Fei, H., Zhang, B., Zhang, T., Zhang, X., Li, S. Z., & Lei, Z. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3233586 · Cited by 41 · see citing works
“Amerini et al. [39] suggested to individuate inter-frame dissimilarities by adopting optical flow fields.”
Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
Ur Rehman Ahmed, N., Badshah, A., Adeel, H., Tajammul, A., Daud, A., & Alsahfi, T. (2025) · IEEE Access · doi:10.1109/access.2024.3523288 · Cited by 45 · see citing works
An integrated spatiotemporal-based methodology for deepfake detection
Ismail, A., Elpeltagy, M. S., Zaki, M. S., & ElDahshan, K. A. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07633-3 · Cited by 46 · see citing works
“The work in [43] exploited the dissimilarities of the optical flow field across frames as a clue to distinguish between real and deepfake videos.”
BackgroundInteractive Two-Stream Network Across Modalities for Deepfake Detection
Wu, J., Zhang, B., Li, Z., Pang, G., Teng, Z., & Jianping Fan, B. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3269841 · Cited by 39 · see citing works
“Amerini et al. [32] extract the optical flow from the original video and use the optical flow image as the input of CNN to improve the accuracy of the model.”
MethodDetection of AI-Manipulated Fake Faces via Mining Generalized Features
Yu, Y., Ni, R., Li, W., & Zhao, Y. (2022) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3499026 · Cited by 51 · see citing works
“[17, 48], and optical flow [2] were adopted to expose fake face videos.”
BackgroundMethodA Review of Deepfake Technology: An Emerging AI Threat
Sharma, M., & Kaur, M. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-5301-8_44 · Cited by 37 · see citing works
3D CNN Architectures and Attention Mechanisms for Deepfake Detection
Roy, R., Joshi, I., Das, A., & Dantcheva, A. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-87664-7_10 · Cited by 36 · see citing works
“Toward thwarting such attacks, early multimedia forensics based detection strategies have been proposed [3, 4, 16, 41].”
BackgroundLearning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection
Xu, Y., Liang, J., Sheng, L., & Zhang, X. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02054-2 · Cited by 41 · see citing works
“In order to enhance the effectiveness of deepfake detectors, numerous studies [35,36,37,38,39] have focused on generating diverse and generic deepfake data.”
Yadav, A. K., & Vishwakarma, D. K. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120898 · Cited by 34 · see citing works
Adaptive Face Forgery Detection in Cross Domain
Song, L., Fang, Z., Li, X., Dong, X., Jin, Z., Chen, Y., & Lyu, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19830-4_27 · Cited by 35 · see citing works
“(2) Freq. temporal feature [4, 34], optical flow [5], frequency [18, 20, 35, 40, 50], local facial region [10, 47, 55], forgery boundary [27] and biometric signals [12, 13, 37], to capture more robust features for forgery detection.”
Background
- Authors
- Amerini, I., Galteri, L., Caldelli, R., & Del Bimbo, A.
- Affiliations
- University of Florence (IT)
- Consorzio Nazionale Interuniversitario per le Telecomunicazioni (IT)
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
- Publisher
- IEEE
- Published
- 2019-10
- Volume
- 2019
- Pages
- 1205-1207
- ISSN
- 2473-9936 (ISSN-L)
- OpenAlex
- W2995516027
- Cited by
- 424
- References
- 14
- Citations by year
- 2026: 35 · 2025: 70 · 2024: 77 · 2023: 95 · 2022: 71 · 2021: 49 · 2020: 27
- FWCI
- 11.98
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- Locations
- IEEE International Conference on Computer Vision Workshops (publishedVersion)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion, other-oa)
- IEEE Conference Proceedings
- 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, optical flow, convolutional neural networks, manipulated video, video forensics, FaceForensics++, fake information
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
