F2Trans: High-Frequency Fine-Grained Transformer for Face Forgery Detection

C Miao, Z Tan, Q Chu, H Liu, H Hu… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
In recent years, face forgery detectors have aroused great interest and achieved impressive
performance, but they are still struggling with generalization and robustness. In this work, we …

UIA-ViT: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection

W Zhuang, Q Chu, Z Tan, Q Liu, H Yuan, C Miao… - European conference on …, 2022‏ - Springer
Intra-frame inconsistency has been proved to be effective for the generalization of face
forgery detection. However, learning to focus on these inconsistency requires extra pixel …

Hierarchical frequency-assisted interactive networks for face manipulation detection

C Miao, Z Tan, Q Chu, N Yu… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Recently, face manipulation techniques have caused increasing trust concerns in our
society. Although current face manipulation detection methods achieve impressive …

Beyond the prior forgery knowledge: Mining critical clues for general face forgery detection

A Luo, C Kong, J Huang, Y Hu… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Face forgery detection is essential in combating malicious digital face attacks. Previous
methods mainly rely on prior expert knowledge to capture specific forgery clues, such as …

A hierarchical feature selection strategy for deepfake video detection

S Mohiuddin, KH Sheikh, S Malakar… - Neural Computing and …, 2023‏ - Springer
Digital face manipulation has become a concern in the last few years due to its harmful
impacts on society. It is especially concerning for high-profile celebrities because their …

MCS-GAN: A different understanding for generalization of deep forgery detection

S **ao, G Lan, J Yang, W Lu, Q Meng… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
After several years of development, deep synthesis technology has made significant
progress in image and video synthesis. Deep forgery represented by Deepfakes has …

Ldfnet: Lightweight dynamic fusion network for face forgery detection by integrating local artifacts and global texture information

Z Guo, L Wang, W Yang, G Yang… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Face forgery detection has become a new research hotspot. Though existing detection
works have achieved impressive performance, they are difficult to achieve a proper trade-off …

Adaptive texture and spectrum clue mining for generalizable face forgery detection

J Liu, J **e, Y Wang, ZJ Zha - IEEE Transactions on Information …, 2023‏ - ieeexplore.ieee.org
Although existing face forgery detection methods achieve satisfactory performance under
closed within-dataset scenario where training and testing sets are created by the same …

Transformer-based feature compensation and aggregation for deepfake detection

Z Tan, Z Yang, C Miao, G Guo - IEEE Signal Processing Letters, 2022‏ - ieeexplore.ieee.org
Deepfake detection has attracted increasing attention in recent years. In this paper, we
propose a transformer-based framework with feature compensation and aggregation (Trans …

DeepFake detection with multi-scale convolution and vision transformer

H Lin, W Huang, W Luo, W Lu - Digital Signal Processing, 2023‏ - Elsevier
With the help of some modern image generative techniques, it is possible to generate or
manipulate image or video contents without introducing any obvious visual artifacts. If these …