FAMM: facial muscle motions for detecting compressed deepfake videos over social networks
As a face manipulation technique, the misuse of Deepfakes poses potential threats to the
state, society, and individuals. Several countermeasures have been proposed to reduce the …
state, society, and individuals. Several countermeasures have been proposed to reduce the …
Texture brush for fashion inspiration transfer: A generative adversarial network with heatmap-guided semantic disentanglement
H Yan, H Zhang, J Shi, J Ma - IEEE Transactions on Circuits …, 2022 - ieeexplore.ieee.org
Automatically accomplishing intelligent fashion design with certain 'inspiration'images can
greatly facilitate a designer's design process, as well as allow users to interactively …
greatly facilitate a designer's design process, as well as allow users to interactively …
Multi-level feature fusion network combining attention mechanisms for polyp segmentation
J Liu, Q Chen, Y Zhang, Z Wang, X Deng, J Wang - Information Fusion, 2024 - Elsevier
Clinically, automated polyp segmentation techniques have the potential to significantly
improve the efficiency and accuracy of medical diagnosis, thereby reducing the risk of …
improve the efficiency and accuracy of medical diagnosis, thereby reducing the risk of …
Eliminating contextual prior bias for semantic image editing via dual-cycle diffusion
The recent success of text-to-image generation diffusion models has also revolutionized
semantic image editing, enabling the manipulation of images based on query/target texts …
semantic image editing, enabling the manipulation of images based on query/target texts …
Poxture: Human posture imitation using neural texture
Human pose imitation, which aims to generate an image with a source character's
appearance, the source character's shape, and a target character's posture, has many …
appearance, the source character's shape, and a target character's posture, has many …
Fakepoi: A large-scale fake person of interest video detection benchmark and a strong baseline
Deepfake technique can synthesize realistic images, audios, and videos, facilitating the
thriving of entertainment, education, healthcare, and other industries. However, its abuse …
thriving of entertainment, education, healthcare, and other industries. However, its abuse …
Few-Shot Generative Model Adaption via Optimal Kernel Modulation
Few-shot generative model adaption is a challenging task that aims to adapt a generative
model pre-trained on a large-scale source domain dataset to the target domain with limited …
model pre-trained on a large-scale source domain dataset to the target domain with limited …
Sdf-3dgan: A 3d object generative method based on implicit signed distance function
In this paper, we develop a new method, termed SDF-3DGAN, for 3D object generation and
3D-Aware image synthesis tasks, which introduce implicit Signed Distance Function (SDF) …
3D-Aware image synthesis tasks, which introduce implicit Signed Distance Function (SDF) …
Self-Calibration Flow Guided Denoising Diffusion Model for Human Pose Transfer
The human pose transfer task aims to generate synthetic person images that preserve the
style of reference images while accurately aligning them with the desired target pose …
style of reference images while accurately aligning them with the desired target pose …
PCFN: progressive cross-modal fusion network for human pose transfer
W Yu, Y Li, R Wang, W Cao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The goal of human pose transfer is to transfer the human in the image from the original pose
to the desired one. Existing methods utilizing progressive manner have achieved great …
to the desired one. Existing methods utilizing progressive manner have achieved great …