TL;DR
The approach begins with detecting the faces and then applying face alignment, crop, resizing, and normalization to guarantee consistency, and has proved to be quite efficient in deepfake detection, as the accuracy of the GRU model was the best, at 98%.
A Deepfake detection framework based on MobileNetV2, which uses effective convolutional feature extraction to accurately classify real and fake facial photos to guarantee consistent input quality and improve the discriminative features for detection is suggested.
This study develops a facial deepfake detection system that integrates YOLOv11 for face detection and the Xception architecture for classifying real and manipulated faces and passed black-box testing.
This study uses ResNet-50 architecture, a well-known Convolutional Neural Network model, to identify tampered videos using DL, and indicates that the proposed model works effectively compared to existing deepfake methods.
Facial Expression Recognition (FER) is an important component of affective computing and human-computer interaction, yet it is difficult to apply in practice because of the variations in illumination, pose variation, occlusions, low-resolution images, and skew in the classes. To overcome these issues, this paper introd...
The results indicate that the combination of facial-region segmentation, latent feature learning and hybrid Transformer architectures enhances the robustness and generalisation capability of deepfake detection significantly.
A novel method for video deepfake detection that assimilates the Pelican Optimization algorithm with a DL model jointly named as Pelican Attention Stacked Bidirectional Long-Short Term Memory (PAttSBiL), aimed at improving recognition accuracy and efficacy is presented.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
