GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer
Open accessThe DOI matches its Crossref record; 71 of the 76 references it cites were found in a registry or an index, and 5 are not checked yet; 1 of the 8 sources its claims cite were checked for support.
Abstract
Deepfakes have raised significant concerns due to their potential to spread false information and compromise the integrity of digital media. Current deepfake detection models often struggle to generalize across a diverse range of deepfake generation techniques and video content. In this work, we propose a Generative Convolutional Vision Transformer (GenConViT) for deepfake video detection. Our model combines ConvNeXt and Swin Transformer models for feature extraction, and it utilizes an Autoencoder and Variational Autoencoder to learn from latent data distributions. By learning from the visual artifacts and latent data distribution, GenConViT achieves an improved performance in detecting a wide range of deepfake videos. The model is trained and evaluated on DFDC, FF++, TM, DeepfakeTIMIT, and Celeb-DF (v2) datasets. The proposed GenConViT model demonstrates strong performance in deepfake video detection, achieving high accuracy across the tested datasets. While our model shows promising results in deepfake video detection by leveraging visual and latent features, we demonstrate that further work is needed to improve its generalizability when encountering out-of-distribution data. Our model provides an effective solution for identifying a wide range of fake videos while preserving the integrity of media.
Verified 2026-10-05 · 5 references not checked yet
Overview
CoChat Summary
TL;DR
GenConViT combines ConvNeXt-Swin hybrid feature extraction with Autoencoder and Variational Autoencoder latent features for deepfake video detection. It achieves strong in-domain results across five datasets, but an out-of-distribution ablation shows substantial generalization failures.
Key findings
- GenConViT reports an average accuracy of 95.8% and an AUC of 99.3% across the tested datasets.
- On DFDC, it reports 98.5% accuracy, 99.9% AUC, and 99.1% F1; on FF++, it reports 97.0% accuracy, 99.6% AUC, and 97.1% F1.
- The full ensemble outperforms its individual networks: networks A and B average 94% accuracy individually, while GenConViT improves over network A by 2.2% and network B by 1.79%.
- In leave-one-dataset-out ablation, performance drops sharply on unseen data: Celeb-DF (v2) held-out accuracy is 55.67% with 11.56% fake accuracy; DFDC held-out is 62.08% with 28.84% fake accuracy; FF++ held-out is 64.86% with 44.20% fake accuracy.
Methods
- Architecture: two independently trained networks. Network A uses an Autoencoder plus ConvNeXt-Swin; network B uses a Variational Autoencoder plus ConvNeXt-Swin. Their real/fake predictions are averaged.
- Data: trained and evaluated on DFDC, FF++, TrustedMedia (TM), DeepfakeTIMIT, and Celeb-DF (v2). Preprocessing yielded 1,004,810 face images split approximately 80:15:5 into 826,756 training, 130,948 validation, and 47,106 test images; video evaluation held back 3,972 videos and averaged predictions over 15 frames per video.
- Training and analysis: Adam optimizer with learning rate 0.0001 and weight decay 0.0001, 30 epochs, batch size 32 for network A and 16 for network B, with Albumentation augmentation. Metrics include accuracy, F1, ROC, and AUC; generalization was tested via leave-one-dataset-out ablation on approximately 5% subsets of training data.
Limitations
- The paper states that GenConViT struggles to generalize to out-of-distribution data, especially more realistic deepfakes, and that deeper or wider CNN architectures did not resolve the domain-shift drop.
- The paper states lower performance on Celeb-DF (v2), attributed to overlapping real/fake latent embeddings in t-SNE visualization, and notes that GenConViT lacks temporal information because it processes frames independently.
- The paper notes that the OOD ablation used randomly selected subsets (about 10k samples per dataset) rather than the full >1M-image training set, and that DFDC/FF++ test subdatasets are usually not shared, so comparisons with prior work are approximate.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
1 Valid · 0 Not valid · 5 Not checked · 50 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“The ConvNeXt-Swin Transformer architecture is a hybrid CNN-Transformer model that combines the strengths of ConvNeXt [34] and Swin Transformer [35] architectures for deepfake detection tasks.”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 3.2. ConvNeXt-Swin Hybrid
What the sources say
- Not checked yetcites [34] Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18–24). A convnet for the 2020s. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA. source
- Supportedcites [35] Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11–17). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada. source
The citation is an identification of the Swin Transformer architecture and the strengths it contributes: our copy's Introduction (p.1) states Swin 'constructs a hierarchical representation... The linear computational complexity is achieved by computing self-attention locally within non-overlapping windows... These merits make Swin Transformer suitable as a general-purpose backbone for various vision tasks,' and the Abstract repeats the same qualities (hierarchy, shifted windows, linear complexity, state-of-the-art results). The ConvNeXt half and the deepfake-detection application belong to the citing authors' hybrid model (and to [34]), not to this source; our copy contains no mention of ConvNeXt or deepfake detection, but nothing in it contradicts what is attributed here. (LLM, conf=0.85)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The proposed GenConViT model demonstrates strong performance in deepfake video detection, achieving high accuracy across the tested datasets.”
- Also stated in: § 4.2. Experimental Results and Discussion · boosted
“The results demonstrate that GenConViT delivers strong performance across various datasets.”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > Abstract
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Also stated in: § 4.2. Experimental Results and Discussion · boosted
In the paper
“Notably, our model is trained (and evaluated) using significantly more datasets than those used for previous models (see Table 1).”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 4.1.2. Datasets
What the sources say
- Not checked yetcites Table 1
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“GenConViT has a total of 695M trainable parameters and requires approximately 6.855 GFLOPs for a single forward pass on a 224 × 224 px input image, and its average per-frame inference time is 0.10 s (NVIDIA RTX 4090 (Santa Clara, CA, USA)).”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 3.2. ConvNeXt-Swin Hybrid
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While networks A and B individually achieve 94% accuracy on average, the full GenConViT ensemble improves upon the average accuracy of network A by 2.2% and network B by 1.79%, indicating the benefit of using both models for detection.”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 4.2. Experimental Results and Discussion
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
33 more claims
Create a free account to see all 56 claims and to verify the 7 references still open.
- Probably not a substantial claim. 8
- It may state two separate claims as one. 11
- The quote only partly states this claim. 1
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
“Wodajo et al. [21] introduced GenConViT, a generative convolutional ViT that integrates convolutional backbones with Transformer modules to model both local textures and global semantics for improved cross-dataset robustness.”
From Cross-dataset video deepfake detection using Transformer and CNN architectures (2026) · cites this paper as [21]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 6. Conclusions
“| FF++ 95.5 | 94.9 | 96.8 |”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 6. Conclusions
“| GenConViT (ours) 97.00 | 99.60 | 97.1 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 3.1. Autoencoder and Variational Autoencoder
“In this case, I B has dimensions 112 × 112 × 3.”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 3.2. ConvNeXt-Swin Hybrid
“Network B has the same configuration as A, but it uses the VAE and outputs both a class prediction probability and a reconstructed image of 224 × 224 × 3 in size.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 1. Introduction
“By training our model on more than 1 million images extracted from five large deepfake datasets and detecting both their visual and latent features, our proposed method aims to enhance its deepfake detection performance compared to that of previously proposed methods.”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 4.1.3. Video Preprocessing
“As a result of applying the preprocessing steps to the datasets, we collected a total of 1,004,810 images.To train, validate, and test our model, the images were divided into a ratio of approximately 80:15:5, resulting in 826,756 images for training, 130,948 images for validation, and 47,106 images for testing.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 4.2. Experimental Results and Discussion
“Note that the TIMIT dataset does not contain any real videos.”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 6. Conclusions
“| | TIMIT | 99.96 | 99.91 | 100.00 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 1. Introduction
“We thoroughly evaluated GenConViT on more than 3972 videos collected from five deepfake video datasets, demonstrating its robust performance under diverse experimental settings.”
§ GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer > 4.1.3. Video Preprocessing
“Namely, for our evaluation, we held back 3972 videos from the DFDC, DeepfakeTIMIT, Celeb-DF (v2), and FF++ datasets for testing.”
Citations
Cites
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534 · cited 2×
“The ConvNeXt-Swin Transformer architecture is a hybrid CNN-Transformer model that combines the strengths of [48] and Swin Transformer [47] architectures for deepfake detection task.”
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · cited 1×
“Paired image-to-image translation GANs [24], [57] are a type of conditional GAN that translate an input image from one domain to another, given input-output pairs of images as training data.”
Generative adversarial networks
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020) · Communications of the ACM · doi:10.1145/3422622 · Cited by 18,384
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 2×
“Several types of GANs have been proposed for face synthesis, including Progressive GANs [27], Wasserstein GANs [2], and Style-Based GANs [28].”
Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01167 · Cited by 8,494
(2017) · International Conference on Machine Learning · Cited by 6,382
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362 · cited 1×
“…generative models like Generative Adversarial Networks (GAN) [16], [28], [52], Variational Autoencoders (VAE) [33], [34], and Diffusion Models (DM) [12] has made it even more challenging to detect deepfakes based on visual artifacts alone since the deepfakes leave small to no trace of visual clues…”
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 1×
“2) Datasets: In our work, we utilized five datasets to train, validate, and test our model: DFDC [13], [14], TrustedMedia (TM) [6], DeepfakeTIMIT (TIMIT) [36], [60], Celeb-DF (v 2 ) [44], [45], and FaceForensics++ (FF++) [58].”
Albumentations: fast and flexible image augmentations
Buslaev, A., Iglovikov, V. I., Khvedchenya, E., Parinov, A., Druzhinin, M., & Kalinin, A. A. (2020) · Information · doi:10.3390/info11020125 · Cited by 2,714 · cited 1×
“The Albumentation [5] library was used for data augmentation, and the following augmentation techniques were used with a strong augmentation rate of 90% : Random-Rotate, Transpose, HorizontalFlip, VerticalFlip, GaussNoise, ShiftScaleRotate, CLAHE, Sharpen, IAAEmboss, Random-BrightnessContrast, and…”
An Introduction to Variational Autoencoders
Kingma, D. P., & Welling, M. (2019) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000056 · Cited by 2,609
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
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 · cited 1×
“2) Datasets: In our work, we utilized five datasets to train, validate, and test our model: DFDC [13], [14], TrustedMedia (TM) [6], DeepfakeTIMIT (TIMIT) [36], [60], Celeb-DF (v 2 ) [44], [45], and FaceForensics++ (FF++) [58].”
Face2Face: Real-Time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Niessner, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.262 · Cited by 1,747
Deferred neural rendering: image synthesis using neural textures
Thies, J., Zollhöfer, M., & Nießner, M. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3323035 · Cited by 1,356 · cited 1×
“The FF++ dataset comprises 1 , 000 original videos collected from YouTube, which have been manipulated using four automated face manipulation methods: Deepfakes, Face2Face, FaceSwap, and NeuralTextures [64].”
Face X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211
Exposing Deep Fakes Using Inconsistent Head Poses
Yang, X., Li, Y., & Lyu, S. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683164 · Cited by 1,196
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 · cited 1×
“Y. Li [42] proposed a model that combines a CNN and a recursive neural network (LRCN) to detect deepfake videos by tracking eye blinking with previous temporal knowledge.”
Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos
Nguyen, H. H., Yamagishi, J., & Echizen, I. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8682602 · Cited by 951
Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations
Matern, F., Riess, C., & Stamminger, M. (2019) · 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw.2019.00020 · Cited by 824 · cited 1×
“Currently, deepfake detection methods often rely heavily on visual features [1], [51], [68], [74].”
Exposing DeepFake Videos By Detecting Face Warping Artifacts
Li, Y., & Lyu, S. (2018) · arXiv · doi:10.48550/arxiv.1811.00656 · Cited by 785 · cited 1×
“Li and Lyu [43] proposed a CNN model for deepfake detection by identifying face-warping artifacts.”
Masood, 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 · cited 2×
“The challenge of detecting deepfakes has inspired researchers and technology companies to develop various deep-learning methods to identify tampered videos [10], [35], [46], [50], [69], [70].”
Fast Face-Swap Using Convolutional Neural Networks
Korshunova, I., Shi, W., Dambre, J., & Theis, L. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.397 · Cited by 501
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
Ciftci, U. A., Demir, I., & Yin, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3009287 · Cited by 499
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 · cited 2×
“The applications of deepfake videos can range from creative uses such as creating realistic special effects or replacing an actor in the film and entertainment industry, to potentially harmful attacks, such as using deepfakes to create misleading videos for criminal purposes [37], [55].”
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. (2019) · arXiv · doi:10.48550/arxiv.1909.11573 · Cited by 464 · cited 2×
“The applications of deepfake videos can range from creative uses such as creating realistic special effects or replacing an actor in the film and entertainment industry, to potentially harmful attacks, such as using deepfakes to create misleading videos for criminal purposes [37], [55].”
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 · cited 1×
“Sabir et al. [59] proposed a Recurrent convolutional model, whereas [11] proposed a Convolutional Vision Transformer (CViT) model.”
Towards Universal Fake Image Detectors that Generalize Across Generative Models
Ojha, U., Li, Y., & Lee, Y. J. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02345 · Cited by 428
Bank, D., Koenigstein, N., & Giryes, R. (2023) · Machine Learning for Data Science Handbook · doi:10.1007/978-3-031-24628-9_16 · Cited by 406
Learning Self-Consistency for Deepfake Detection
Zhao, T., Xu, X., Xu, M., Ding, H., Xiong, Y., & Xia, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01475 · Cited by 383 · cited 1×
“Zhao et al. [78] proposed a pair-wise self-consistency learning with an inconsistency image generator to train a ConvNet [48] that extracts local source features and measures their self-consistency to identify Deepfakes.”
Image-to-Image Translation: Methods and Applications
Pang, Y., Lin, J., Qin, T., & Chen, Z. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3109419 · Cited by 378
Multi-Region Probabilistic Histograms for Robust and Scalable Identity Inference
Sanderson, C., & Lovell, B. C. (2009) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-01793-3_21 · Cited by 301 · cited 1×
“2) Datasets: In our work, we utilized five datasets to train, validate, and test our model: DFDC [13], [14], TrustedMedia (TM) [6], DeepfakeTIMIT (TIMIT) [36], [60], Celeb-DF (v 2 ) [44], [45], and FaceForensics++ (FF++) [58].”
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 · cited 2×
“…cut-out [30] DFDC (with face cut-out augmentation) STDT [77] FF++, Celeb-DF ViT with distillation [21] DFDC Heo et. al [22] DFDC Coccomini et. al [9] FF++, DFDC Li et. al [41] FF++, CelebA-HQ (FaceShifter GAN) GenConViT (ours) FF++, DFDC, TM, Celeb (v2), TIMIT TABLE I: Datasets used in selected…”
TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization
Guillaro, F., Cozzolino, D., Sud, A., Dufour, N., & Verdoliva, L. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01974 · Cited by 275 · cited 1×
“Another approach to spotting deepfake videos involves examining the consistency of pixels or groups of similar pixels [19].”
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
Yu, N., Skripniuk, V., Abdelnabi, S., & Fritz, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01418 · Cited by 195 · cited 1×
“…detection methods, such as utilizing biological signals [8], geometric features [73], frequency information [71], spatial features with temporal information [32], [77] and generative adversarial network fingerprints [75], as potential solutions to the difficulties of detecting deepfakes.”
Countering 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 · cited 1×
“Recently, deepfakes have become a public concern due to their potential for misuse and the spread of false information [10], [25], [76].”
Spatiotemporal Inconsistency Learning for DeepFake Video Detection
Gu, Z., Chen, Y., Yao, T., Ding, S., Li, J., Huang, F., & Ma, L. (2021) · Proceedings of the 29th ACM International Conference on Multimedia · doi:10.1145/3474085.3475508 · Cited by 189 · cited 1×
“The visual features-based detection can be on a frame-per-frame basis [22] or temporal relationship between differences be-tween frames through time [18], [29].”
One Shot Face Swapping on Megapixels
Zhu, Y., Li, Q., Wang, J., Xu, C., & Sun, Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00480 · Cited by 175 · cited 1×
“Face swapping [38], [40], [79] is the process of replacing a person’s face in an image or video with the face of another person to create a non-existent realistic face.”
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 150 · cited 3×
“…DFDC CViT [11] DFDC Random cut-out [30] DFDC (with face cut-out augmentation) STDT [77] FF++, Celeb-DF ViT with distillation [21] DFDC Heo et. al [22] DFDC Coccomini et. al [9] FF++, DFDC Li et. al [41] FF++, CelebA-HQ (FaceShifter GAN) GenConViT (ours) FF++, DFDC, TM, Celeb (v2), TIMIT TABLE I:…”
Generative Adversarial Networks for Face Generation: A Survey
Kammoun, A., Slama, R., Tabia, H., Ouni, T., & Abid, M. (2023) · ACM Computing Surveys · doi:10.1145/3527850 · Cited by 132 · cited 1×
“Face synthesis [26] is a method of synthesizing desired non-existent face images based on a given input image.”
FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
Li, H., Zhou, J., Li, Y., Wu, B., Wu, B., & Dong, J. (2024) · neural information processing systems · doi:10.52202/079017-1429 · Cited by 121
A 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 113 · cited 2×
“The challenge of detecting deepfakes has inspired researchers and technology companies to develop various deep-learning methods to identify tampered videos [10], [35], [46], [50], [69], [70].”
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) · SSRN Electronic Journal · doi:10.2139/ssrn.4030341 · Cited by 112
TALL: Thumbnail Layout for Deepfake Video Detection
Xu, Y., Liang, J., Jia, G., Yang, Z., Zhang, Y., & He, R. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02071 · Cited by 109
FreqBlender: Enhancing DeepFake Detection by Blending Frequency KnowledgePreprint
Li, H., Zhou, J.-R., Li, Y.-Z., et al. (2024) · Neural Information Processing Systems · doi:10.48550/arxiv.2404.13872 · Cited by 97
Video Transformer for Deepfake Detection with Incremental Learning
Khan, S. A., & Dai, H. (2021) · Proceedings of the 29th ACM International Conference on Multimedia · doi:10.1145/3474085.3475332 · Cited by 79 · cited 4×
“The visual features-based detection can be on a frame-per-frame basis [22] or temporal relationship between differences be-tween frames through time [18], [29].”
InfluentialDiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
Sun, K., Chen, S., Yao, T., Liu, H., Sun, X., Ding, S., & Ji, R. (2024) · neural information processing systems · doi:10.52202/079017-3218 · Cited by 77
AnyFace: Free-style Text-to-Face Synthesis and Manipulation
Sun, J., Deng, Q., Li, Q., Sun, M., Ren, M., & Sun, Z. (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/cvpr52688.2022.01813 · Cited by 76
Handbook of Digital Face Manipulation and Detection: From DeepFakes to Morphing Attacks
(2022) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-030-87664-7 · Cited by 72
Machine Learning for Data Science Handbook
Rokach, L., Maimon, O., & Shmueli, E. (2023) · Springer eBooks · doi:10.1007/978-3-031-24628-9 · Cited by 65
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 54 · cited 1×
“Chintha et al. [7] proposed a modified XceptionNet architecture, which incorporates visual frames, edge maps, and dense optical flow maps alongside RGB channel data to target low-level features.”
Nguyen, H. H., Tieu, T. N.-D., Nguyen-Son, H.-Q., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · Proceedings of the 13th International Conference on Availability, Reliability and Security · doi:10.1145/3230833.3230863 · Cited by 52 · cited 1×
“MesoNet [1] is a deep-fake detection method that uses CNNs to extract mesoscopic properties and identify deepfakes created with techniques like Deepfake [53] and Face2Face [65].”
Deepfake Video Detection with Spatiotemporal Dropout Transformer
Zhang, D., Lin, F., Hua, Y., Wang, P., Zeng, D., & Ge, S. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3547913 · Cited by 50 · cited 4×
“Some models excelled in additional metrics, such as the STDT [77] model with 97 .”
InfluentialVasist, P. N., & Krishnan, S. (2022) · Internet Research · doi:10.1108/intr-06-2022-0465 · Cited by 49 · cited 1×
“The challenge of detecting deepfakes has inspired researchers and technology companies to develop various deep-learning methods to identify tampered videos [10], [35], [46], [50], [69], [70].”
Deepfake Detection with Deep Learning: Convolutional Neural Networks versus Transformers
Thing, V. L. L. (2023) · 2023 IEEE International Conference on Cyber Security and Resilience (CSR) · doi:10.1109/csr57506.2023.10225004 · Cited by 48 · cited 2×
“00 - Thing [66] 92 .”
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 · cited 1×
“The challenge of detecting deepfakes has inspired researchers and technology companies to develop various deep-learning methods to identify tampered videos [10], [35], [46], [50], [69], [70].”
Detection of AI-Generated Synthetic Faces
Gragnaniello, D., Marra, F., & Verdoliva, L. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-87664-7_9 · Cited by 44 · cited 1×
“To this effect, various authors have proposed deepfake detection techniques that use different approaches, including visual features, biological signals, and frequency information, to name a few [17], [49].”
Hybrid Transformer Network for Deepfake Detection
Khan, S. A., & Dang-Nguyen, D.-T. (2022) · International Conference on Content-based Multimedia Indexing · doi:10.1145/3549555.3549588 · Cited by 43 · cited 2×
“61 - Random cut-out [30] 98 .”
Dual-Generator Face Reenactment
Hsu, G.-S., Tsai, C.-H., & Wu, H.-Y. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00072 · Cited by 41 · cited 1×
“Face reenactment [23], [62], [65] is a face synthesis method that transfers source face attributes to a target face while preserving the appearance and identity of the target face’s features.”
Real Appearance Modeling for More General Deepfake Detection
Tian, J., Cai, Y., Wang, X., Chen, P., Xiao, Z., Dai, J., Han, J., & Chai, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72943-0_23 · Cited by 40
Convolutional Neural Networks: A Comprehensive Survey
Haridas, R., & Jyothi, R. L. (2019) · International Journal of Applied Engineering Research · doi:10.37622/ijaer/14.3.2019.780-789 · Cited by 37 · cited 1×
“Convolutional Neural Networks (CNNs) [20], [56] are also used for face synthesis by learning the mapping between a face image and its attributes, such as facial expression, age, and gender.”
Misleading Deep-Fake Detection with GAN Fingerprints
Wesselkamp, V., Rieck, K., Arp, D., & Quiring, E. (2022) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw54247.2022.9833860 · Cited by 36
Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning
Le, B. M., & Woo, S. S. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02045 · Cited by 36
An Introduction to Digital Face Manipulation
Tolosana, R., Vera-Rodríguez, R., Fiérrez, J., Morales, A., & Ortega-García, J. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-87664-7_1 · Cited by 36 · cited 1×
“Deep-fake videos are produced by superimposing one person’s facial features onto another person’s face through techniques such as face replacement, facial reenactment, face editing, and complete face synthesis [50], [67], among others.”
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 · cited 1×
“The challenge of detecting deepfakes has inspired researchers and technology companies to develop various deep-learning methods to identify tampered videos [10], [35], [46], [50], [69], [70].”
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 31 · cited 1×
“Currently, deepfake detection methods often rely heavily on visual features [1], [51], [68], [74].”
Face Forgery Detection Based on Facial Region Displacement Trajectory Series
Sun, Y., Zhang, Z., Echizen, I., Nguyen, H. H., Qiu, C., & Sun, L. (2023) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw58289.2023.00070 · Cited by 30 · cited 1×
“Sun et al. [63] proposed a virtual-anchor-based approach to robustly extract the facial trajectory, capturing displacement information.”
Generalized Facial Manipulation Detection with Edge Region Feature Extraction
Kim, D.-K., & Kim, K. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00284 · Cited by 27 · cited 2×
“D. Kim and K. Kim [32] proposed a facial forensic framework that uses pixel-level color features in the edge region of an image and a 3D-CNN classification model to interpret the extracted color features spatially and temporally for generalized and robust face manipulation detection.”
Masked Conditional Diffusion Model for Enhancing Deepfake Detection
Chen, T., Yang, S., Hu, S., Fang, Z., Fu, Y., Wu, X., & Wang, X. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651330 · Cited by 22
Improved Deepfake Video Detection Using Convolutional Vision Transformer
Deressa, D. W., Lambert, P., Van Wallendael, G., Atnafu, S., & Mareen, H. (2024) · 2024 IEEE Gaming, Entertainment, and Media Conference (GEM) · doi:10.1109/gem61861.2024.10585593 · Cited by 20 · cited 3×
“60 - CViT [11] 91 .”
Self-citationDigital Manipulation and the Future of Electoral Democracy in the U.S.
Zachary, G. P. (2020) · IEEE Transactions on Technology and Society · doi:10.1109/tts.2020.2992666 · Cited by 19 · cited 1×
“Recently, deepfakes have become a public concern due to their potential for misuse and the spread of false information [10], [25], [76].”
Toward the Creation and Obstruction of DeepFakes
Li, Y., Sun, P., Qi, H., & Lyu, S. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-87664-7_4 · Cited by 11 · cited 1×
“2) Datasets: In our work, we utilized five datasets to train, validate, and test our model: DFDC [13], [14], TrustedMedia (TM) [6], DeepfakeTIMIT (TIMIT) [36], [60], Celeb-DF (v 2 ) [44], [45], and FaceForensics++ (FF++) [58].”
The Threat of Deepfakes to Computer and Human Visions
Korshunov, P., & Marcel, S. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-87664-7_5 · Cited by 10 · cited 1×
“The applications of deepfake videos can range from creative uses such as creating realistic special effects or replacing an actor in the film and entertainment industry, to potentially harmful attacks, such as using deepfakes to create misleading videos for criminal purposes [37], [55].”
Trusted Media Challenge Dataset and User Study
Chen, W., Chua, S. L. B., Winkler, S., & Ng, S.-K. (2022) · Proceedings of the 31st ACM International Conference on Information & Knowledge Management · doi:10.1145/3511808.3557715 · Cited by 7 · cited 1×
“2) Datasets: In our work, we utilized five datasets to train, validate, and test our model: DFDC [13], [14], TrustedMedia (TM) [6], DeepfakeTIMIT (TIMIT) [36], [60], Celeb-DF (v 2 ) [44], [45], and FaceForensics++ (FF++) [58].”
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable DiffusionPreprint
Sun, K., Shen, C., Yao, T., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.04372 · Cited by 5
Bhattacharyya, C., Wang, H., Zhang, F., Kim, S., & Zhu, X. (2024) · arXiv · doi:10.48550/arxiv.2404.01579 · Cited by 4
COM-PRESS: Dashboard to Detect (AI-Based) Image Manipulations
Mareen, H., D’haeseleer, S., Damme, K. V., Evens, T., Lambert, P., & Wallendael, G. V. (2024) · IEEE Gaming, Entertainment, and Media Conference (GEM) · doi:10.1109/gem61861.2024.10585560 · Cited by 2
Self-citation
Research works printed but not linked: 14
- Liu, P., Lin, Y., He, Y., Wei, Y., Zhen, L., Zhou, J.T., Goh, R.S.M., and Liu, J. (2021). Automated deepfake detection. arXiv.
- Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
- Kingma, D.P., and Welling, M. (2022). Auto-Encoding Variational Bayes. arXiv.
- Yan, Z., Sun, P., Lang, Y., Du, S., Zhang, S., Wang, W., and Liu, L. (2022). Multimodal graph learning for deepfake detection. arXiv.
- Li, B., Sun, J., Poskitt, C.M., and Wang, X. (2024). How Generalizable are Deepfake Image Detectors? An Empirical Study. arXiv.
- O’shea, K., and Nash, R. (2015). An introduction to convolutional neural networks. arXiv.
- Li, L., Bao, J., Yang, H., Chen, D., and Wen, F. (2020). FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping. arXiv.
- Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2018). Progressive Growing of GANs for Improved Quality, Stability, and Variation. arXiv.
- Heo, Y.J., Choi, Y.J., Lee, Y.W., and Kim, B.G. (2021). Deepfake Detection Scheme Based on Vision Transformer and Distillation. arXiv.
- Dolhansky, B., Howes, R., Pflaum, B., Baram, N., and Ferrer, C.C. (2019). The Deepfake Detection Challenge (DFDC) Preview Dataset. arXiv.
- Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., and Ferrer, C.C. (2020). The DeepFake Detection Challenge (DFDC) Dataset. arXiv.
- Korshunov, P., and Marcel, S. (2018). DeepFakes: A New Threat to Face Recognition? Assessment and Detection. arXiv.
- Bazarevsky, V., Kartynnik, Y., Vakunov, A., Raveendran, K., and Grundmann, M. (2019). BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs. arXiv.
- Maiano, L., Casadei, F., and Amerini, I. (2025). Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection. arXiv.
Cited by
Diffusion model in modern detection: Advancing Deepfake techniques
Siddiqui, F., Yang, J., Xiao, S., & Fahad, M. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113922 · Cited by 33
Cross-dataset video deepfake detection using Transformer and CNN architectures
Petmezas, G. (2026) · Machine Vision and Applications · doi:10.1007/s00138-026-01809-w · Cited by 6
“…Video Swin Transformer [20] capture long-range dependencies and global spatiotemporal context that CNNs often miss. Building on this, Wodajo et al. [21] introduced GenConViT, a generative convolutional ViT that integrates convolutional backbones with Trans-former modules to model both local…”
Deepfake Detection via a Progressive Attention Network
Guo, S., Gao, M., Li, Q., Jeon, G., & Camacho, D. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650463 · Cited by 10
“Wodajo et al. [12] combined the learning capabilities of CNNs and transformers to detect deepfake video.”
BackgroundGLAD-ViT: Global–Local Attention Duality in Vision Transformers for Deepfake Detection
Pandey, P. K., Solanki, A., & Sharma, S. K. (2026) · IETE Technical Review · doi:10.1080/02564602.2026.2621327 · Cited by 3
“Unlike existing convolution-heavy hybrids like Gen-ConViT [10] or attention-based ViT models that apply attention modules externally only on 25 facial landmarks [12], the proposed GLAD-ViT introduces a dual-attention mechanism within each transformer encoder layer to process the entire facial…”
InfluentialMulti-modal texture fusion network for detecting AI-generated images
Yu, H., & Xu, B. H. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1663292 · Cited by 9
Metadata
- Authors
- Deressa, D. W., Mareen, H., Lambert, P., Atnafu, S., Akhtar, Z., & Van Wallendael, G.
- Affiliations
- IDLab, Department of Electronics and Information Systems, Ghent University—imec, 9000 Gent, Belgium
- Ghent University (BE)
- Addis Ababa University (ET)
- SUNY Polytechnic Institute (US)
- ORCID
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2025-06-12
- Volume
- 15
- Issue
- 12
- Pages
- 6622
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W4411241923
- Cited by
- 46
- References
- 66
- Citations by year
- 2026: 31 · 2025: 12
- FWCI
- 14.88
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- Ghent University Academic Bibliography (Ghent University) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Funders
- Addis Ababa University Research Grant for the Adaptive Problem-Solving Research (AR/048/2021, G0A2523N)
- Research Foundation—Flanders (AR/048/2021, G0A2523N)
- Flemish government (AR/048/2021, G0A2523N)
- IDLab (Ghent University—imec) (AR/048/2021, G0A2523N)
- Flanders Innovation and Entrepreneurship (VLAIO) (AR/048/2021, G0A2523N)
- European Union (AR/048/2021, G0A2523N)
- 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 video detection, ConvNeXt, Swin Transformer, variational autoencoder, autoencoder, latent space distribution, visual artifacts, media integrity, out-of-distribution generalization
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.
A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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
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.