Generalized Deepfake Video Detection Through Time-Distribution and Metric Learning

Saif, Shahela; Tehseen, Samabia; Ali, Syed Taha; Kausar, Sumaira; Jameel, Amina

doi:10.1109/mitp.2022.3168351

Cited by 7 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the low performance on test videos from a different manipulation technique, the reported results confirmed the superiority of the 3D‐CNN against the baselines used for comparison. Furthermore, recent studies reported outstanding results in temporal learning domain (Elpeltagy et al, 2023; Saif et al, 2022; Sun et al, 2023).…”

Section: Discussion and Open Issuesmentioning

confidence: 99%

“…(Saif et al, 2022) proposed a method for face forgery detection in videos by a deep temporal learning architecture based on LSTM. The authors used the contrastive loss function for the cross‐learning aspects of pairs of real and faked video frames.…”

Section: Deepfake Detection Methods Reviewmentioning

confidence: 99%

“…The proposed model yielded 0.908 AUC and 90.7% accuracy with the frame's spatial representation obtained by the DenseNet-121 and two LSTM layers for temporal learning. (Saif et al, 2022) proposed a method for face forgery detection in videos by a deep temporal learning architecture based on LSTM. The authors used the contrastive loss function for the cross-learning aspects of pairs of real and faked video frames.…”

Section: Lstmmentioning

confidence: 99%

See 2 more Smart Citations

A review of deep learning‐based approaches for deepfake content detection

Passos,

Jodas,

Costa

et al. 2024

Expert Systems

View full text Add to dashboard Cite

Recent advancements in deep learning generative models have raised concerns as they can create highly convincing counterfeit images and videos. This poses a threat to people's integrity and can lead to social instability. To address this issue, there is a pressing need to develop new computational models that can efficiently detect forged content and alert users to potential image and video manipulations. This paper presents a comprehensive review of recent studies for deepfake content detection using deep learning‐based approaches. We aim to broaden the state‐of‐the‐art research by systematically reviewing the different categories of fake content detection. Furthermore, we report the advantages and drawbacks of the examined works, and prescribe several future directions towards the issues and shortcomings still unsolved on deepfake detection.

show abstract

Section: Discussion and Open Issuesmentioning

confidence: 99%

Section: Deepfake Detection Methods Reviewmentioning

confidence: 99%

Section: Lstmmentioning

confidence: 99%

See 1 more Smart Citation

A review of deep learning‐based approaches for deepfake content detection

Passos,

Jodas,

Costa

et al. 2024

Expert Systems

View full text Add to dashboard Cite

show abstract

“…El Rai et al [51] proposed a novel approach to capture the potential noise disturbance from any video manipulation procedure. Despite being a simple approach, the main drawback regards using a small number of videos for training and evaluat- Furthermore, recent studies reported outstanding results in temporal learning domain [92,74,75].…”

Section: Recent Architectures Overviewmentioning

confidence: 99%

“…Moreover, there is a challenge in reaching the same best-performing accuracy for different fake production methods. Most related studies provided lower accuracy for the NeuralTextures and FaceShifter manipulation of the FaceForensics++ dataset [82,92,75]. It shows an urge to explore more complex forgery traits produced by several manipulation techniques and the challenges towards developing more accurate methods for fake face detection;…”

Section: Opportunities and Future Challengesmentioning

confidence: 99%

A Review of Deep Learning-based Approaches for Deepfake Content Detection

Passos,

Jodas,

Costa

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent advancements in deep learning generative models have raised concerns as they can create highly convincing counterfeit images and videos. This poses a threat to people's integrity and can lead to social instability. To address this issue, there is a pressing need to develop new computational models that can efficiently detect forged content and alert users to potential image and video manipulations. This paper presents a comprehensive review of recent studies for deepfake content detection using deep learning-based approaches. We aim to broaden the state-of-the-art research by systematically reviewing the different categories of fake content detection. Furthermore, we report the advantages and drawbacks of the examined works and future directions towards the issues and shortcomings still unsolved on deepfake detection.

show abstract

DT-TransUNet: A Dual-Task Model for Deepfake Detection and Segmentation

Zheng,

Zhou,

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Generalized Deepfake Video Detection Through Time-Distribution and Metric Learning

Cited by 7 publications

References 13 publications

A review of deep learning‐based approaches for deepfake content detection

A review of deep learning‐based approaches for deepfake content detection

A Review of Deep Learning-based Approaches for Deepfake Content Detection

DT-TransUNet: A Dual-Task Model for Deepfake Detection and Segmentation

Contact Info

Product

Resources

About