The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
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.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“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]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“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.
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
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
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
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 2,801
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
The computation of optical flow
Beauchemin, S. S., & Barron, J. A. (1995) · ACM Computing Surveys · doi:10.1145/212094.212141 · Cited by 1,313
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
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 702
Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., & Nießner, M. (2016) · ACM SIGGRAPH Emerging Technologies · doi:10.1145/2929464.2929475 · Cited by 589
Flagged first, then by citations
Cited by
Sorted by citations
Items 101–200 of 425
Deepfakes: evolution and trends
Gil, R., Virgili‐Gomà, J., López, J. M., & Garcı́a, R. (2023) · Soft Computing · doi:10.1007/s00500-023-08605-y · Cited by 46
“…et al. (2021), Carlini and Farid (2020), Tursman et al. (2020), Kaur et al. (2020), Masi et al. (2020), Feng et al. (2020), Maksutov et al. (2020), Amerini et al. (2019b), Javed et al. (2021), Kuang et al. (2021), Patil et al. (2021), Megías et al. (2021), Patil and Chouragade (2021), Xu et al.…”
Emergence of deepfakes and video tampering detection approaches: A survey
Kingra, S., Aggarwal, N., & Kaur, N. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13100-x · Cited by 33
“This goal was further pursued in [8] by analyzing optical flow of concerned video sequence to exploit inter-frame dissimilarities.”
BackgroundMethodDigital Face Manipulation Creation and Detection: A Systematic Review
Dang, M. H., & Nguyen, T. N. (2023) · Electronics · doi:10.3390/electronics12163407 · Cited by 39
Advancements in detecting Deepfakes: AI algorithms and future prospects − a review
Singh, L. H., Charanarur, P., & Chaudhary, N. K. (2025) · Discover Internet of Things · doi:10.1007/s43926-025-00154-0 · Cited by 46
“Evaluating the reliability of optical flow fields for Deepfake video identification by testing them against more datasets and with other neural networks and studying how this approach can be combined with frame-based methodologies to improve performance [48].”
Finding Facial Forgery Artifacts with Parts-Based Detectors
Schwarcz, S. L., & Chellappa, R. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00104 · Cited by 34
“Many techniques take advantage of the strength of deep networks directly, by training image classifiers with various architectures to identify forgeries, either through RGB [4, 2, 23, 7] or optical flow [3].”
BackgroundA comprehensive evaluation of feature-based AI techniques for deepfake detection
Sandotra, N., & Arora, B. (2024) · Neural Computing and Applications · doi:10.1007/s00521-023-09288-0 · Cited by 37
“Amerini et al. [115] utilised optical flow approach to discriminate altered videos based on temporal clues.”
DeepFake Detection using a frame based approach involving CNN
Ajoy, A., Mahindrakar, C. U., Gowrish, D., & Vinay, A. (2021) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca51532.2021.9544734 · Cited by 33
Visual User-Generated Content Verification in Journalism: An Overview
Khan, S. A., Sheikhi, G., Opdahl, A. L., Rabbi, F., Stoppel, S., Trattner, C., & Dang‐Nguyen, D. (2023) · IEEE Access · doi:10.1109/access.2023.3236993 · Cited by 36
A deep learning model for FaceSwap and face-reenactment deepfakes detection
Nawaz, M., Javed, A., & Irtaza, A. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111854 · Cited by 37
Deep Fake Image Detection using Xception Architecture
Joshi, P., & Nivethitha, V. (2024) · International Conference on Recent Trends in Computer Science and Technology (ICRTCST) · doi:10.1109/icrtcst61793.2024.10578398 · Cited by 33
Exposing Vulnerabilities of Deepfake Detection Systems with Robust Attacks
Hussain, S., Neekhara, P., Dolhansky, B., Bitton, J., Ferrer, C. C., McAuley, J., & Koushanfar, F. (2021) · Digital Threats Research and Practice · doi:10.1145/3464307 · Cited by 35
“The state-of-the-art methods for detecting manipulated facial content in videos rely on Convolutional Neural Networks (CNNs) [1, 2, 21, 43, 56, 57].”
MethodGong, D. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/58932020 · Cited by 31
“Amerini proposed to use optical flow field to develop possible interframe differences[76].”
BackgroundTrans-DF: A Transfer Learning-based end-to-end Deepfake Detector
Patel, M. M., Gupta, A., Tanwar, S., & Obaidat, M. S. (2020) · International Conference on Computing, Communication and Automation · doi:10.1109/iccca49541.2020.9250803 · Cited by 36
“While [10] used the CNN with optical flow for Deepfake detection and achieved a benchmark accuracy of 81.61%, [11] and [12] proposed CNN architectures combined with Long Short Term Memory (LSTM) networks, with the former achieving accuracy of 94.29%, and the latter achieving an F1 score of 0.95.”
MethodInfluentialLBPNet: Exploiting texture descriptor for deepfake detection
Kingra, S., Aggarwal, N., & Kaur, N. (2022) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2022.301452 · Cited by 33
Deepfakes Examiner: An End-to-End Deep Learning Model for Deepfakes Videos Detection
Ilyas, H., Irtaza, A., Javed, A., & Malik, K. M. (2022) · International Conference on Open Source Systems and Technologies (ICOSST) · doi:10.1109/icosst57195.2022.10016871 · Cited by 33
“For instance, considering the FaceForensics++ (FF++) dataset, methods such as [14,16,18,25] are not evaluated on all the available subsets of the dataset.”
BackgroundMethodResultInfluentialDetecting GANs and Retouching based Digital Alterations via DAD-HCNN
Jain, A., Majumdar, P., Singh, R., & Mayank Vatsa, A. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00344 · Cited by 27
“[4] detected deepfake videos by exploiting inter-frame dissimilarities, unlike previous work that focuses on single-frame detection.”
MethodShort And Low Resolution Deepfake Video Detection Using CNN
Rahman, A., Siddique, N., Moon, M. J., Tasnim, T., Islam, M., Shahiduzzaman, M., & Ahmed, S. (2022) · IEEE Region Humanitarian Technology Conference · doi:10.1109/r10-htc54060.2022.9929719 · Cited by 31
“In the paper Deepfake Video Detection through Optical Flow-based CNN [25], they proposed a deep learning technique for the creation and processing of multimedia content.”
MethodInfluentialMINTIME: Multi-Identity Size-Invariant Video Deepfake Detection
Coccomini, D. A., Zilos, G. K., Amato, G., Caldelli, R., Falchi, F., Papadopoulos, S., & Gennaro, C. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3409054 · Cited by 33
“Proposals have also been made that exploit the optical flow of video [4] or analyze the relationships between audio peaks and video content [35].”
BackgroundSelf-citationA Review of Deep Learning-based Approaches for Deepfake Content Detection
Passos, L. A., Jodas, D., Costa, K. A. P., Júnior, L. A. S., Rodrigues, D., Ser, J. D., Camacho*, D., & Papa, J. (2023) · doi:10.22541/au.169735672.27713914/v1 · Cited by 116
DeepFake Videos Detection Using Self-Supervised Decoupling Network
Zhang, J., Ni, J., & Xie, H. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428368 · Cited by 28
“FaceForensics++ (FF++) [6] is a recently released benchmark dataset and widely used for performance evaluation of face forgery detection [12, 21, 22].”
BackgroundDeepfake Detection by Exploiting Surface Anomalies: The Surfake Approach
Ciamarra, A., Caldelli, R., Becattini, F., Seidenari, L., & Del Bimbo, A. (2024) · 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00112 · Cited by 27
“Amerini et al. [4] leveraged the optical flow in order to look at motion discrepancies, which are found across synthetically generated frames, and finally to classify them as original or deceptive.”
BackgroundSelf-citationGeneralizable Deepfake Detection With Phase-Based Motion Analysis
Prashnani, E., Goebel, M. G., & Manjunath, B. S. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3441821 · Cited by 34
“Traditionally, temporal methods for DF detection either use hand-coded features such as estimating motion vectors [6] or landmark trajectories [59], or learn tempo-”
MethodAW-MSA: Adaptively weighted multi-scale attentional features for DeepFake detection
Yadav, A. K., & Vishwakarma, D. K. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107443 · Cited by 30
Investigating the Impact of Pre-processing and Prediction Aggregation on the DeepFake Detection TaskPreprint
Charitidis, P., Kordopatis-Zilos, G., Papadopoulos, S., & Kompatsiaris, I. Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07084 · Cited by 42
“In [15] the optical flow is estimated to exploit temporal discrepancies among frames.”
BackgroundMethodA hierarchical feature selection strategy for deepfake video detection
Mohiuddin, S., Sheikh, K. H., Malakar, S., Velásquez, J. D., & Sarkar, R. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08201-z · Cited by 25
“Amerini et al. [30] used the unusual motion of facial components for deepfake detection.”
BackgroundDeep learning technology for face forgery detection: A survey
Ma, L., Yang, P., Xu, Y., Yang, Z., Li, P., & Huang, H. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.129055 · Cited by 31
Xiao, S., Lan, G., Yang, J., Li, Y., & Wen, J. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3213832 · Cited by 27
“D CNN is proposed to fuse the spatial and temporal features, and its performance is superior to other latest DF detection research [31].”
BackgroundUsing Deep Learning to Detecting Deepfakes
Mallet, J., Dave, R., Seliya, N., & Vanamala, M. (2022) · 2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi56532.2022.10068449 · Cited by 26
Ahmed, S. R., & Sonuç, E. (2023) · Soft Computing · doi:10.1007/s00500-023-09245-y · Cited by 25
RetractedA spatio-frequency cross fusion model for deepfake detection and segmentation
Zheng, J., Zhou, Y., Zhang, N., Hu, X., Xu, K., Gao, D., & Tang, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129683 · Cited by 29
Dynamic-Aware Federated Learning for Face Forgery Video Detection
Hu, Z., Xie, H., Yu, L., Gao, X., Shang, Z., & Zhang, Y. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3501814 · Cited by 29
“al.[3] propose a detection method based on optical low.”
MethodWaterLo: Protect Images from Deepfakes Using Localized Semi-Fragile Watermark
Beuve, N., Hamidouche, W., & Olivier Déforges, A. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00046 · Cited by 26
“…explored traces left in other components of videos, such as the frequency domain using techniques like Discrete Cosine Transform (DCT) [12] or Fourier transform [11], motion analysis using Euler video magnification [6], optical flows [1], or texture analysis using Local Binary Pattern (LBP) [17].”
Datasets, clues and state-of-the-arts for multimedia forensics: An extensive review
Yadav, A. K., & Vishwakarma, D. K. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123756 · Cited by 25
TCSD: Triple Complementary Streams Detector for Comprehensive Deepfake Detection
Liu, X., Yu, Y., Li, X., Zhao, Y., & Guo, G. (2022) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3558004 · Cited by 23
“Although an existing method [5] makes use of such information, the features extracted by their method are rough, and it is still necessary to design more effective methods to mine the discriminative clues from FBI.”
BackgroundMethodProtecting World Leader Using Facial Speaking Pattern Against Deepfakes
Chu, B., You, W., Yang, Z., Zhou, L., & Wang, R. (2022) · IEEE Signal Processing Letters · doi:10.1109/lsp.2022.3205562 · Cited by 27
Improving Deepfake Detection by Mixing Top Solutions of the DFDC
Trabelsi, A., Pic, M. M., & Dugelay, J. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909905 · Cited by 24
“For detection methods based on image or texture analysis, the authors mainly look for inconsistencies in optical flow [5] or the presence of artifacts [15].”
MethodFighting Deepfake by Residual Noise Using Convolutional Neural Networks
Rai, M. C. E., Al-Ahmad, H., Gouda, O. M., Hejji, D. J., Talib, M. W. A., & Nasir, Q. (2020) · International Conference on Signal Processing and Information Security (ICSPIS) · doi:10.1109/icspis51252.2020.9340138 · Cited by 26
“The results obtained for FaceForensics are close to those obtained in [11] and better than the results obtained in [6].”
MethodResultTowards Benchmarking and Evaluating Deepfake Detection
Deng, J., Lin, C., Hu, P., Shen, C. Q., Wang, Q., Li, Q. L., & Li, Q. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3369711 · Cited by 38
Liu, D., Chen, T., Peng, C., Wang, N., Hu, R., & Gao, X. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3516561 · Cited by 22
“Amerini et al. [16], on the other hand, proposed an optical flow method to compute the inter-frame differences and feeding them into a convolutional neural network for fake video detection.”
MethodExposing DeepFake Videos Using Attention Based Convolutional LSTM Network
Su, Y., Xia, H., Liang, Q., & Nie, W. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10588-6 · Cited by 23
Image quality assessment based fake face detection
Kiruthika, S. U., & Masilamani, V. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11493-9 · Cited by 23
“Nhu et al. have proposed a deep learning classifier based on VGG-16 model [39] outperforms ImageNet and ResNet50 where the weights are assigned from the deep face recognition system developed using VGG-Net and achieved the accuracy of 80% on data from AI Challenge contest.”
MethodDeepfake Generation and Detection - An Exploratory Study
Garg, D., & Gill, R. (2023) · IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON) · doi:10.1109/upcon59197.2023.10434896 · Cited by 31
Dimitri, G. M. (2022) · Computers · doi:10.3390/computers11110163 · Cited by 22
Narrowing Domain Gaps With Bridging Samples for Generalized Face Forgery Detection
Yu, Y., Ni, R., Yang, S., Zhao, Y., & Kot, A. C. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3310341 · Cited by 22
Video face forgery detection via facial motion-assisted capturing dense optical flow truncation
Yang, G., Xu, K., Fang, X., & Zhang, J. (2022) · The Visual Computer · doi:10.1007/s00371-022-02683-z · Cited by 21
Multimodal Automated Fact-Checking: A Survey
Akhtar, M., Schlichtkrull, M., Guo, Z., Cocarascu, O., Simperl, E. P. B., & Vlachos, A. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.361 · Cited by 34
Jayashre, K., & Amsaprabhaa, M. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103860 · Cited by 26
Deepfake Detection with Clustering-based Embedding Regularization
Zhu, K., Wu, B., & Wang, B. (2020) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc50466.2020.00046 · Cited by 23
“[31] propose a new forensic technique which can discern between fake and original video sequences.”
BackgroundExposing Deep-faked Videos by Anomalous Co-motion Pattern DetectionPreprint
Wang, G., Zhou, J., & Wu, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04848 · Cited by 29
“In [3], while the researchers have similarly attempted establishing a forensic pipeline on top of motion features, we have outperformed its performance by approx.”
BackgroundMethodInfluentialRedhaei, A. A., Fraihat, S., & Al‐Betar, M. A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11286-8 · Cited by 19
“…employed pre-trained models like VGG, ResNet, Inception, MobileNet, DenseNet, and Xception, fine-tuned on deepfake datasets to detect artifacts and inconsisten - cies introduced during the deepfake generation process (Li and Lyu 2018; Amerini et al. 2019; Suratkar et al. 2020; Zhang and Liu 2020).”
Cross-Dataset Face Manipulation Detection
Bekci, B., Akhtar, Z., & Ekenel, H. K. (2020) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu49456.2020.9302157 · Cited by 19
“biological-based [8], [9] [10]; handcrafted feature [11], [12] or deep learning-based [13], [6], [14].”
MethodKuang, L., Wang, Y., Hang, T., Chen, B., & Zhao, G. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11539-y · Cited by 22
“The compared seven models contains three spatial ones (MesoNet [1], Xception [25], and OC-FakeDec [17]) and four temporal ones (Optical Flow Features [3], C3D [11], CNN-LSTM [26], and S-MIL [21]).”
BackgroundMethodInfluentialDeepMark: A Scalable and Robust Framework for DeepFake Video Detection
Li, T., Ye, Q., Hu, H., Xue, Q., Xiao, Y., & Li, J. (2023) · ACM Transactions on Privacy and Security · doi:10.1145/3629976 · Cited by 24
“DeepFake technology [11, 27, 44–46, 52] is witnessing a rapid advancement and In recent years, there have been many efforts to identify DeepFakes by passively capturing the artifacts introduced during manipulations [1, 8, 15, 18, 30, 51, 54, 64].”
BackgroundMethodRobust Frame-Level Detection for Deepfake Videos With Lightweight Bayesian Inference Weighting
Zhou, L., Ma, C., Wang, Z., Zhang, Y., Shi, X., & Wu, L. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3337128 · Cited by 21
“Four meth-ods are used for generating deepfake videos, including DeepFaceLab [19], FS, FS-Gan [18], Recycle-Gan [35], and ALAE [36].”
BackgroundMethodTriple-modality interaction for deepfake detection on zero-shot identity
Yoon, J., Panizo-LLedot, Á., Camacho, D., & Choi, C. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102424 · Cited by 22
Exploiting Facial Symmetry to Expose Deepfakes
Li, G., Cao, Y., & Zhao, X. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506272 · Cited by 19
Light-weight 3DCNN for DeepFakes, FaceSwap and Face2Face facial forgery detection
Kohli, A., & Gupta, A. K. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12778-3 · Cited by 18
“[1] method for VGG16 and ResNet50, respectively.”
MethodInfluentialAsha, S., Vinod, P., & Menon, V. G. (2023) · International Journal of Information Security · doi:10.1007/s10207-023-00695-x · Cited by 18
“A deepfake detection model [16] used the adoption of optical flow fields to exploit possible inter-frame dissimilarities using CNN.”
BackgroundMethodBi-Source Reconstruction-Based Classification Network for Face Forgery Video Detection
Zhang, D., Fu, C., Lu, D., Li, J., & Zhang, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3330390 · Cited by 22
“The correlation between the visual and audio of faces in the video [23], [24], and detecting inter-frame anomaly of fake video [25], [26], [27], [28], [29], [30].”
BackgroundDeepfake Detection Using EfficientNet and XceptionNet
Yasser, B., Hani, J., Elgayar, S., Amgad, O., Ahmed, N., Ebied, H. M., Amr, H., & Salah, M. (2023) · International Conference on Intelligent Computing and Information Systems (ICICIS) · doi:10.1109/icicis58388.2023.10391114 · Cited by 19
“Other approaches used optical flow fields, capsule networks, and CNN architectures like VGG and ResNet [9].”
MethodDemystifying Attention Mechanisms for Deepfake Detection
Das, A., Das, S., & Dantcheva, A. (2021) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg52635.2021.9667026 · Cited by 17
Detecting Digital Deception: A CNN-RNN hybrid Approach of Deepfake Detection
Singh, H., Kumar, R., Gupta, M., & Chilluri, V. S. B. (2025) · International Conference on Pervasive Computational Technologies (ICPCT) · doi:10.1109/icpct64145.2025.10940830 · Cited by 16
“The strength of architectures is the interconnection of spatial and temporal characteristics to be posted efficiently and timely [15].”
Kou, Y., Li, P., Ma, H., Zhou, J., Huang, Z. A., & Li, X. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11225-7 · Cited by 17
“Amerini et al. ( 2019 ), combined with the inconsistency of optical flow field, proposed a detection method based on dynamic features, which can effectively deal with the inconsis - tency problem across sequences.”
Forgery face detection via adaptive learning from multiple experts
Fu, X., Li, S., Yuan, Y., Li, B., & Li, X. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.01.017 · Cited by 17
Deepfake: An Endanger to Cyber Security
Sudhakar, K. V. S., & Shanthi, M. (2023) · International Conference on Sustainable Computing and Smart Systems (ICSCSS) · doi:10.1109/icscss57650.2023.10169246 · Cited by 16
“Amerini et al, [14] Authors proposed a method which exploits the optical flow field dissimilarities between original and fake videos.”
MethodTwo-Stream Xception Structure Based on Feature Fusion for DeepFake Detection
Wang, B., Huang, L., Huang, T., & Ye, F. (2023) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-023-00312-8 · Cited by 17
DeepFake Detection using 3D-Xception Net with Discrete Fourier Transformation
Biswas, A., Bhattacharya, D., & Kumar, K. A. (2021) · Journal of Information Systems and Telecommunication (JIST) · doi:10.52547/jist.9.35.161 · Cited by 14
“Amerini et al [15] suggest a method of deepfake detection that relies on computing the optical flow of the given video.”
MethodTemporal Deepfake Generation and Detection in Video Sequences Using Recurrent Neural Networks (RNNs)
Iyengar, S. S., Nabavirazavi, S., Hariprasad, Y., Prasad, H. B., & Mohan, C. K. (2025) · Signals and communication technology · doi:10.1007/978-3-031-89327-8_11 · Cited by 15
SDHF: Spotting DeepFakes with Hierarchical Features
Liang, T., Chen, P., Zhou, G., Gao, H., Liu, J., Li, Z., & Dai, J. (2020) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai50040.2020.00108 · Cited by 15
“Meanwhile, some previous clip-based works tried to leverage RNN [10] or optical flow [11] to capture manipulation traces in temporal, which demand a small interval between frames in the clip.”
BackgroundIR-Capsule: Two-Stream Network for Face Forgery Detection
Lin, K., Han, W., Li, S., Gu, Z., Zhao, H., Ren, J., Zhu, L., & Lv, J. (2022) · Cognitive Computation · doi:10.1007/s12559-022-10008-4 · Cited by 16
“A different view from other methods was proposed in [51], which used the optical flow fields to exploit possible inter-frame differences.”
MethodAdversarial Attack on Deepfake Detection Using RL Based Texture Patches
Fernandes, S. L., & Jha, S. K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-66415-2_14 · Cited by 15
Sar, A., Sati, S., Choudhury, T., Joshi, P., Sille, R., Srihari, K., & Bansal, K. (2025) · IEEE Access · doi:10.1109/access.2025.3550770 · Cited by 19
FMFCC-V: An Asian Large-Scale Challenging Dataset for DeepFake Detection
Li, G., Zhao, X., Cao, Y., Pei, P., Li, J., & Zhang, Z. (2022) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/3531536.3532946 · Cited by 14
“The anomalies between consecutive frames such as optical flow motion [15], eye blinking pattern [35], facial action units [14] and heart rate [23] have been exploited to detect DeepFake videos.”
MethodAttacker Attribution of Audio Deepfakes
Müller, N., Diekmann, F., & Williams, J. R. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-129 · Cited by 14
HEVC based tampered video database development for forensic investigation
Singla, N., Singh, J., Nagpal, S., & Tokas, B. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-14303-y · Cited by 14
“Content-based forgery detection extracts geometrical [16, 46, 72], optical-flow [5, 54, 65], textural [10], or statistical features [25, 64, 66, 71] from video frames that can be utilised for detection of tampering.”
BackgroundOn the effectiveness of handcrafted features for deepfake video detection
Kaddar, B., Fezza, S. A., Hamidouche, W., Akhtar, Z., Hadid, A., Serra-Sagrista, J. S., Hernández-Cabronero, M., & Sanchez, V. (2023) · Journal of Electronic Imaging · doi:10.1117/1.jei.32.5.053033 · Cited by 15
“55, the authors refined the attention of the network by monitoring the optical flow of frames.”
BackgroundUndercover Deepfakes: Detecting Fake Segments in Videos
Saha, S., Perera, R. D., Seneviratne, S., Malepathirana, T., Rasnayaka, S., Geethika, D., Sim, T., & Halgamuge, S. K. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00048 · Cited by 16
DIP: Diffusion Learning of Inconsistency Pattern for General DeepFake Detection
Nie, F., Ni, J., Zhang, J., Zhang, B., & Zhang, W. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3521766 · Cited by 17
“Adirectionalinconsistencydecoderisadopted accordingly,wheredirection-awareattentionandinconsistencydiffusionareincorporatedtoexplorepotentialinconsistency patternsandjointlylearntheinherentrelationships.”
MMD Based Discriminative Learning for Face Forgery Detection
Han, J., & Gevers, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69541-5_8 · Cited by 15
“[25] propose an optical flow based CNN for deep fake video detection.”
BackgroundObject-based forgery detection in surveillance video using capsule network
Bakas, J., Naskar, R., Nappi, M., & Bakshi, S. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03511-3 · Cited by 14
“It assumes that image/video coding artifacts, statistical or some other intrinsic characteristics (Castiglione et al. 2011; Aghamaleki and Behrad 2016; Amerini et al. 2019) are altered due to the manipulation.”
BackgroundFace Forgery Detection Based on the Improved Siamese Network
Wang, B., Li, Y., Wu, X., Ma, Y., Song, Z., & Wu, M.-K. (2022) · Security and Communication Networks · doi:10.1155/2022/5169873 · Cited by 14
DEEP MOVEMENT: Deep learning of movie files for management of endovascular thrombectomy
Kelly, B. S., Martinez, M. L., Do, H. M., Hayden, J., Huang, Y., Yedavalli, V. S., Ho, C. Y., Keane, P. A., Killeen, R. P., Lawlor, A., et al. (2023) · European Radiology · doi:10.1007/s00330-023-09478-3 · Cited by 14
“Methods such as optical flow are traditionally used [24–26].”
DeepFake Videos Detection Using Crowd Computing
Salini, Y., & HariKiran, J. (2024) · International Journal of Information Technology · doi:10.1007/s41870-023-01494-2 · Cited by 13
Detecting AI-Generated Images Using a Hybrid ResNet-SE Attention Model
Gunukula, A. R., Gupta, H. D., & Sheng, V. S. (2025) · Applied Sciences · doi:10.3390/app15137421 · Cited by 19
UAM‐Net : Robust Deepfake Detection Through Hybrid Attention Into Scalable Convolutional Network
Sudarshana, K., & Yendapalli, V. (2025) · Expert Systems · doi:10.1111/exsy.70009 · Cited by 17
“Amerini et al. (2019) used an optical flow-based CNN to exploit inter-frame dissimilarities.”
An Overview of Face Manipulation Detection
Ju, X. (2020) · Journal of Cyber Security · doi:10.32604/jcs.2020.014310 · Cited by 13
“[53] CNN + Optical Flow FF++ (F2F) ACC = 0.”
BackgroundDeepfake Video Detection Based on Improved CapsNet and Temporal–Spatial Features
Lu, T., Bao, Y., & Li, L. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.034963 · Cited by 15
A comprehensive study on multimedia DeepFakes
Boutadjine, A., Harrag, F., Shaalan, K. F., & Karboua, S. (2023) · International Conference on Advances in Electronics, Control and Communication Systems (ICAECCS) · doi:10.1109/icaeccs56710.2023.10104814 · Cited by 14
“In order to detect obvious semantic distortions in DeepFakes, early face forgery detection systems like [2], [7] often use the standard pipeline of learning convolutional neural networks (CNN) for image classification.”
MethodInfluentialDeepfake source detection in a heart beat
Çiftçi, U. A., Demir, İ., & Yin, L. (2023) · The Visual Computer · doi:10.1007/s00371-023-02981-0 · Cited by 16
Latent Flow Diffusion for Deepfake Video Generation
Aashish Chandra, K., Aashutosh, A. V., Das, S., & Das, A. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00382 · Cited by 12
“FF++ is a forensics dataset consisting of 1000 original video sequences that have been manipulated with three automated face manipulation methods[2]: Deepfakes[5], Face2Face[43] and NeuralTextures[42].”
MethodEvaluating Robustness of Sequence-based Deepfake Detector Models by Adversarial Perturbation
Shahriyar, S. A., & Wright, M. (2022) · doi:10.1145/3494109.3527194 · Cited by 12
Das, S., Kolahdouzi, M., Özparlak, L., Hickie, W., & Etemad, A. (2023) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb57857.2023.10449301 · Cited by 11
“Prior works such as [2, 6, 46, 26] have used optical flow features followed by a classifier for deepfake detection.”
MethodFace Forgery Detection Based On Segmentation Network
Zhou, Y., Luo, A., Kang, X., & Lyu, S. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506371 · Cited by 11
“Besides, due to the lack of time continuity in deepfake videos, time continuity analysis [20][21][22] and biological signal detection [23] were also utilized to capture the discrepancy between genuine and manipulated videos.”
MethodSWYNT: Swin Y-Net Transformers for Deepfake Detection
Khalid, F., Akbar, M. H., & Gul, S. (2023) · International Conference on Robotics and Automation in Industry (ICRAI) · doi:10.1109/icrai57502.2023.10089585 · Cited by 13
“Table II further shows that current approaches, such as [11, 26] reported detection accuracy on three to four subsets of the FF++ dataset, whereas [17] published findings on just one subset.”
BackgroundMethodInfluentialEdwards curve digital signature algorithm for video integrity verification on blockchain framework
Lawrence, L., & Shreelekshmi, R. (2024) · Science & Justice · doi:10.1016/j.scijus.2024.04.008 · Cited by 11
Cyber Security Focused Deepfake Detection System Using Big Data
Kumar, N., & Kundu, A. (2024) · SN Computer Science · doi:10.1007/s42979-024-03105-8 · Cited by 12
“The realm of deepfake video detection delves into the analysis of optical flow fields [ 22], showcasing promising accuracy with VGG16 and ResNet50, though requiring further evaluation for real-time processing.”
A New Approach for Deepfake Detection with the Choquet Fuzzy Integral
Karaköse, M., İlhan, İ., Yetış, H., & Ataş, S. (2024) · Applied Sciences · doi:10.3390/app14167216 · Cited by 13
Lyu, S. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-16-7621-5_12 · Cited by 11
A Feature Fusion Based Deep Learning Model for Deepfake Video Detection
Mohiuddin, S., Ganguly, S., Malakar, S., Kaplun, D., & Sarkar, R. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-030-97020-8_18 · Cited by 11
Extracting Local Information from Global Representations for Interpretable Deepfake Detection*
Soltandoost, E., Plesh, R. O., Schuckers, S., Peer, P., & Štruc, V. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00177 · Cited by 10
“Early DeepFake detectors were mostly based on known shortcomings of deepfake generation approaches and strived to detect explicit traces of the generation process [1,3,14,20,62].”
Metadata
- 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
