Multimodal research in vision and language: A review of current and emerging trends
Deep Learning and its applications have cascaded impactful research and development
with a diverse range of modalities present in the real-world data. More recently, this has …
with a diverse range of modalities present in the real-world data. More recently, this has …
A survey and taxonomy of adversarial neural networks for text‐to‐image synthesis
Text‐to‐image synthesis refers to computational methods which translate human written
textual descriptions, in the form of keywords or sentences, into images with similar semantic …
textual descriptions, in the form of keywords or sentences, into images with similar semantic …
Application of integrated steganography and image compressing techniques for confidential information transmission
BK Pandey, D Pandey, S Wairya… - Cyber security and …, 2022 - Wiley Online Library
In the present day, images and videos account for nearly 80% of all the data transmitted
during our daily activities. This work employs a combination of novel stegnography and data …
during our daily activities. This work employs a combination of novel stegnography and data …
RiFeGAN: Rich feature generation for text-to-image synthesis from prior knowledge
Text-to-image synthesis is a challenging task that generates realistic images from a textual
sequence, which usually contains limited information compared with the corresponding …
sequence, which usually contains limited information compared with the corresponding …
Dual alignment unsupervised domain adaptation for video-text retrieval
Video-text retrieval is an emerging stream in both computer vision and natural language
processing communities, which aims to find relevant videos given text queries. In this paper …
processing communities, which aims to find relevant videos given text queries. In this paper …
Knowing what to learn: a metric-oriented focal mechanism for image captioning
Despite considerable progress, image captioning still suffers from the huge difference in
quality between easy and hard examples, which is left unexploited in existing methods. To …
quality between easy and hard examples, which is left unexploited in existing methods. To …
CKD: Cross-task knowledge distillation for text-to-image synthesis
Text-to-image synthesis (T2IS) has drawn increasing interest recently, which can
automatically generate images conditioned on text descriptions. It is a highly challenging …
automatically generate images conditioned on text descriptions. It is a highly challenging …
Recent advances of image steganography with generative adversarial networks
J Liu, Y Ke, Z Zhang, Y Lei, J Li, M Zhang… - IEEE Access, 2020 - ieeexplore.ieee.org
In the past few years, the Generative Adversarial Network (GAN), which proposed in 2014,
has achieved great success. There have been increasing research achievements based on …
has achieved great success. There have been increasing research achievements based on …
Semi-supervised medical report generation via graph-guided hybrid feature consistency
Medical report generation generates the corresponding report according to the given
radiology image, which has been attracting increasing research interest. However, existing …
radiology image, which has been attracting increasing research interest. However, existing …
Image caption generation using visual attention prediction and contextual spatial relation extraction
R Sasibhooshan, S Kumaraswamy, S Sasidharan - Journal of Big Data, 2023 - Springer
Automatic caption generation with attention mechanisms aims at generating more
descriptive captions containing coarser to finer semantic contents in the image. In this work …
descriptive captions containing coarser to finer semantic contents in the image. In this work …