ICH-PRNet: a cross-modal intracerebral haemorrhage prognostic prediction method using joint-attention interaction mechanism
Accurately predicting intracerebral hemorrhage (ICH) prognosis is a critical and
indispensable step in the clinical management of patients post-ICH. Recently, integrating …
indispensable step in the clinical management of patients post-ICH. Recently, integrating …
Vision+ language applications: A survey
Text-to-image generation has attracted significant interest from researchers and practitioners
in recent years due to its widespread and diverse applications across various industries …
in recent years due to its widespread and diverse applications across various industries …
UNet-like network fused swin transformer and CNN for semantic image synthesis
A Ke, J Luo, B Cai - Scientific Reports, 2024 - nature.com
Semantic image synthesis approaches has been dominated by the modelling of
Convolutional Neural Networks (CNN). Due to the limitations of local perception, their …
Convolutional Neural Networks (CNN). Due to the limitations of local perception, their …
Face photo–sketch synthesis via intra-domain enhancement
Face photo–sketch synthesis plays an increasingly important role in the field of law
enforcement and entertainment. However, most of the existing methods only focus on how to …
enforcement and entertainment. However, most of the existing methods only focus on how to …
Collaborative-GAN: An approach for stabilizing the training process of generative adversarial network
Generative Adversarial Network (GAN) outperforms its peers in the generative models'
family and is widely used to generate realistic samples in various domains. The basic idea of …
family and is widely used to generate realistic samples in various domains. The basic idea of …
LSG-GAN: Latent space guided generative adversarial network for person pose transfer
Y Lu, B Gu, W Ouyang, Z Liu, F Zou, J Hou - Knowledge-Based Systems, 2023 - Elsevier
Person pose transfer is a popular subject in computer vision tasks and is widely used in
image editing, virtual try-on, and game designing. Most of the state-of-the-art models are …
image editing, virtual try-on, and game designing. Most of the state-of-the-art models are …
Dynamically optimized human eyes-to-face generation via attribute vocabulary
Generating face from human eyes, named eyes-to-face generation, is an interesting
research topic of face synthesis, which has great potential in the field of public security. One …
research topic of face synthesis, which has great potential in the field of public security. One …
Semi-supervised cross-modal hashing with joint hyperboloid map**
H Fu, G Gu, Y Dou, Z Li, Y Zhao - Knowledge-Based Systems, 2024 - Elsevier
By using a small amount of label information to achieve favorable performance, semi-
supervised methods are more practical in real-world application scenarios. However …
supervised methods are more practical in real-world application scenarios. However …
ISF-GAN: Imagine, Select, and Fuse with GPT-Based Text Enrichment for Text-to-Image Synthesis
Text-to-Image synthesis aims to generate an accurate and semantically consistent image
from a given text description. However, it is difficult for existing generative methods to …
from a given text description. However, it is difficult for existing generative methods to …
MRD‐GAN: Multi‐representation discrimination GAN for enhancing the diversity of the generated data
The generative adversarial network (GAN) is a highly effective member of the generative
models category and is extensively employed for generating realistic samples across …
models category and is extensively employed for generating realistic samples across …