A comprehensive overview of Deepfake: Generation, detection, datasets, and opportunities

JW Seow, MK Lim, RCW Phan, JK Liu - Neurocomputing, 2022 - Elsevier
When used maliciously, deepfake can pose detrimental implications to political and social
forces including reducing public trust in institutions, damaging the reputation of prominent …

Image processing using multi-code gan prior

J Gu, Y Shen, B Zhou - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
Despite the success of Generative Adversarial Networks (GANs) in image synthesis,
applying trained GAN models to real image processing remains challenging. Previous …

Unsupervised multi-target domain adaptation: An information theoretic approach

B Gholami, P Sahu, O Rudovic… - … on Image Processing, 2020 - ieeexplore.ieee.org
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where
there is a single, labeled, source and a single target domain. However, in many real-world …

Style transfer for co-speech gesture animation: A multi-speaker conditional-mixture approach

C Ahuja, DW Lee, YI Nakano, LP Morency - Computer Vision–ECCV 2020 …, 2020 - Springer
How can we teach robots or virtual assistants to gesture naturally? Can we go further and
adapt the gesturing style to follow a specific speaker? Gestures that are naturally timed with …

No gestures left behind: Learning relationships between spoken language and freeform gestures

C Ahuja, DW Lee, R Ishii… - Findings of the Association …, 2020 - aclanthology.org
We study relationships between spoken language and co-speech gestures in context of two
key challenges. First, distributions of text and gestures are inherently skewed making it …

[PDF][PDF] IRC-GAN: Introspective Recurrent Convolutional GAN for Text-to-video Generation.

K Deng, T Fei, X Huang, Y Peng - IJCAI, 2019 - ijcai.org
Automatically generating videos according to the given text is a highly challenging task,
where visual quality and semantic consistency with text are two critical issues. In existing …

Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects

NUR Ahmed, A Badshah, H Adeel, A Tajammul… - IEEE …, 2024 - ieeexplore.ieee.org
In recent years, rapid advancements in deepfakes (incorporating Artificial Intelligence (AI),
machine, and deep learning) have updated tools and techniques for manipulating …

Atgan: Adversarial training-based gan for improving adversarial robustness generalization on image classification

D Wang, W **, Y Wu, A Khan - Applied Intelligence, 2023 - Springer
Deep neural networks are vulnerable to adversarial examples, which are well-designed
examples aiming to cause models to produce wrong outputs with high confidence. Although …

[PDF][PDF] Real-Time Deepfake Image Generation Based on Stylegan2-ADA.

DA Talib, AA Abed - Revue d'Intelligence Artificielle, 2023 - researchgate.net
Accepted: 28 March 2023 Training Generative Adversarial Networks (GAN) usually leads to
hyper-specialization due to few data and this causes training to diverge. This paper …

[CITATION][C] A Style-Based Generator Architecture for Generative Adversarial Networks

T Karras - arxiv preprint arxiv:1812.04948, 2019