The DOI matches its Crossref record; 38 of the 40 references it cites were found in a registry or an index.
A Hybrid CNN-LSTM model for Video Deepfake Detection by Leveraging Optical Flow Features
Open accessAbstract
Deepfakes are the synthesized digital media in order to create ultra-realistic fake videos to trick the spectator. Deep generative algorithms, such as, Generative Adversarial Networks(GAN) are widely used to accomplish such tasks. This approach synthesizes pseudo-realistic contents that are very difficult to distinguish by traditional detection methods. In most cases, Convolutional Neural Network(CNN) based discriminators are being used for detecting such synthesized media. However, it emphasise primarily on the spatial attributes of individual video frames, thereby fail to learn the temporal information from their inter-frame relations. In this paper, we leveraged an optical flow based feature extraction approach to extract the temporal features, which are then fed to a hybrid model for classification. This hybrid model is based on the combination of CNN and recurrent neural network (RNN) architectures. The hybrid model provides effective performance on open source data-sets such as, DFDC, FF++ and Celeb-DF. This proposed method shows an accuracy of 66.26%,91.21% and 79.49% in DFDC, FF++, and Celeb-DF respectively with a very reduced No of sample size of$\leq 100$samples(frames). This promises early detection of fake contents compared to existing modalities.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“By combining the spatial awareness of CNNs with the temporal analysis capabilities of LSTMs, this model achieved 66.26% accuracy on the DFDC dataset, demonstrating its effectiveness [11].”
From Enhancing Deepfake Detection Through Quantum Transfer Learning and Class-Attention Vision Transformer Architecture (2025) · cites this paper as [11]
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“”ImageNet” [32], hence effective for modelling vision related problems [33].”
BackgroundXception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380 · cited 3×
“as, VGG16 [26], InceptionV3 [27], ResNet50 [28], Xception [29], MobileNetV2 [30], EfficientNetB7 [31].”
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072 · cited 4×
“EfficientNetB7 is giving better accuracy for Celeb-DF dataset with 50 frames and VGG16 is the second best for the same.”
InfluentialHorn, B. K. P., & Schunck, B. G. (1981) · Artificial Intelligence · doi:10.1016/0004-3702(81)90024-2 · Cited by 10,312
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332
Weiss, K., Khoshgoftaar, T. M., & Wang, D. (2016) · Journal of Big Data · doi:10.1186/s40537-016-0043-6 · Cited by 6,260
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 · cited 5×
“In this table only frames upto 40 have been considered for DFDC dataset and upto 70 frames for FaceForensics++ to reduce computational complexity.”
MethodInfluentialDlib-ml: A Machine Learning Toolkit
King, D. E. (2009) · doi:10.5555/1577069.1755843 · Cited by 2,777
MesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872
Research works printed but not linked: 2
- ajder, 2019, The state of deepfakes: Landscape, threats, and impact, Amsterdam Deeptrace, 27
- geitgey, 2019, Face recognition documentation, Release 1 2 1, 3, 3
Cited by
CIFAKE: 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 265
“Similarly, convolutional and temporal techniques were proposed in [21] to achieve 66.26% to 91.21% accuracy in a mixed set of synthetic data detection datasets.”
MethodInfluentialA review of deep learning‐based approaches for deepfake content detection
(2024) · doi:10.1111/exsy.13570 · Cited by 116
FedForgery: Generalized Face Forgery Detection With Residual Federated Learning
Liu, D., Dang, Z., Peng, C., Zheng, Y., Li, S., Wang, N., & Gao, X. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3293951 · Cited by 95
“[24] described a CNN model based on optical flow volume, pre-trained CNN model and LSTM layer to model the inconsistent motion of each pixel in a video frame, so as to distinguish the true and false video.”
MethodDeepfake video detection methods, approaches, and challenges
Alrashoud, M. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.04.007 · Cited by 49
cao, F., & Jian, Y. (2023) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2023.168200 · Cited by 66
Metadata
- Authors
- Saikia, P., Dholaria, D., Yadav, P., Patel, V., & Roy, M.
- Affiliations
- School of Technology Information & Communication Technology,Computer Science and Engineering Department
- Pandit Deendayal Energy University (IN)
- Venue
- 2022 International Joint Conference on Neural Networks (IJCNN)
- Publisher
- IEEE
- Published
- 2022-07-18
- Pages
- 1-7
- ISSN
- 2161-4407 (ISSN-L)
- OpenAlex
- W4312758842
- Cited by
- 133
- References
- 40
- Citations by year
- 2026: 25 · 2025: 48 · 2024: 35 · 2023: 21 · 2022: 4
- FWCI
- 9.79
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International Joint Conference on Neural Networks (IJCNN) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, video forgery detection, optical flow features, temporal feature extraction, CNN-LSTM hybrid model, generative adversarial networks, synthetic media, DFDC, Celeb-DF
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A Hybrid CNN-LSTM model for Video Deepfake Detection by Leveraging Optical Flow Features. https://app.cochat.ai/papers/10.1109/ijcnn55064.2022.9892905
- The paper
- Saikia, P., Dholaria, D., Yadav, P., Patel, V., & Roy, M. (2022). A Hybrid CNN-LSTM model for Video Deepfake Detection by Leveraging Optical Flow Features. 2022 International Joint Conference on Neural Networks (IJCNN). https://doi.org/10.1109/ijcnn55064.2022.9892905
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.