Enhanced deepfake detection with densenet and cross-vit
Integrity signals
Registry
Cites
Statistics
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?
Cross-dataset evaluation is essential for assessing deepfake detection models.
“Cross-dataset evaluation is essential, as demonstrated by [13], whose DenseNet-CrossViT hybrid maintained performance in FaceForensics ++, Celeb-DF and DeeperForensics 1.0 by combining local and global feature analysis.”
From Beyond Accuracy: A Deployment-Oriented Benchmark of Deepfake Detection Models (2025) · cites this paper as [13]
CrossViT employs two parallel transformer encoders: one with small patches to capture fine-grained local artifacts, and another with large patches to model global contextual relationships.
“The model employs two parallel transformer encoders: one with small patches (e.g., 16 × 16) to capture fine-grained local artifacts (e.g., texture inconsistencies, high-frequency noise), and another with large patches (e.g., 32 × 32) to model global contextual relationships (e.g., semantic coherence, lighting consistency).”
From Beyond Accuracy: A Deployment-Oriented Benchmark of Deepfake Detection Models (2025) · cites this paper as [13]
FaceForensics++ includes 1,000 videos per manipulation method across multiple resolutions (480p-1080p) and compression levels (LQ).
“FaceForensics++ [13] includes 1,000 videos per manipulation method across multiple resolutions (480p-1080p) and compression levels (LQ), providing a comprehensive evaluation framework.”
From Beyond Accuracy: A Deployment-Oriented Benchmark of Deepfake Detection Models (2025) · cites this paper as [13]
CrossViT's branches are fused iteratively using a Cross-Attention Fusion Module (CAFM), enabling bidirectional feature interaction between scales.
“These branches are fused iteratively using a Cross-Attention Fusion Module (CAFM), which enables bidirectional feature interaction between scales, allowing detailed local features to inform global understanding and vice versa.”
From Beyond Accuracy: A Deployment-Oriented Benchmark of Deepfake Detection Models (2025) · cites this paper as [13]
Cites
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 21,793 · see citing works
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846 · see citing works
Deep Fakes: A Looming Challenge for Privacy, Democracy, and National Security
Chesney, R., & Citron, D. K. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3213954 · Cited by 880 · see citing works
DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
Jiang, L., Li, R., Wu, W., Qian, C., & Loy, C. C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00296 · Cited by 599 · see citing works
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497 · see citing works
Deepfake detection using deep learning methods: A systematic and comprehensive review
Heidari, A., Jafari Navimipour, N., Dag, H., & Unal, M. (2024) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1520 · Cited by 349 · 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
BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs
Bazarevsky, V., Kartynnik, Y., Vakunov, A., Raveendran, K., & Grundmann, M. (2019) · arXiv · doi:10.48550/arxiv.1907.05047 · Cited by 264 · see citing works
Deepfake 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
Deep fake detection and classification using error-level analysis and deep learning
Rafique, R., Gantassi, R., Amin, R., Frnda, J., Mustapha, A., & Alshehri, A. H. (2023) · Scientific Reports · doi:10.1038/s41598-023-34629-3 · Cited by 155 · see citing works
Exploiting Style Latent Flows for Generalizing Deepfake Video Detection
Choi, J., Kim, T., Jeong, Y., Baek, S., & Choi, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00114 · Cited by 84 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Beyond Accuracy: A Deployment-Oriented Benchmark of Deepfake Detection Models
Ain, Q. U., Ning, H., Philipo, A. G., Daneshmand, M., & Ding, J. (2025) · Preprint (TechRxiv) · doi:10.36227/techrxiv.176315939.91577661/v1 · Cited by 2 · see citing works
- Authors
- Siddiqui, F., Yang, J., Xiao, S., & Fahad, M.
- Affiliations
- Tianjin University (CN)
- Corresponding author
- Xiao, Shuai
- Venue
- Expert Systems with Applications
- Publisher
- Elsevier BV
- Published
- 2025-04
- Volume
- 267
- Pages
- 126150
- ISSN
- 0957-4174 (ISSN-L)
- OpenAlex
- W4405493872
- Cited by
- 62
- References
- 11
- Citations by year
- 2026: 31 · 2025: 31
- FWCI
- 8.68
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Expert Systems with Applications (publishedVersion)
- Funders
- National Natural Science Foundation of China (62271345, 62301356)
- 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, DenseNet, vision transformer, hybrid CNN-ViT model, voting mechanism, multi-face detection, misinformation
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
