A TextCNN and WGAN-gp based deep learning frame for unpaired text style transfer in multimedia services

Hu, Mingxuan; He, Min; Su, Wei; Chehri, Abdellah

doi:10.1007/s00530-020-00714-0

Cited by 12 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, when CNN models extract features of occluded faces, the obstructed parts are embedded in the latent space representation [22]. (2) Algorithms based on generative adversarial networks [23]: GAN [24], WGAN [25], WGAN-GP [26], LSGAN [27], DCGAN [28], etc. These models generate clearer and more realistic samples, but suffer from poor training stability, gradient vanishing, and mode collapse issues.…”

Section: Related Workmentioning

confidence: 99%

WITHDRAWN: Masked face recognition with BF-FaceNet and multi-view features

Sun

et al. 2023

Preprint

View full text Add to dashboard Cite

Wearing masks in accordance with scientific guidelines is the most economically-effective protective measure for preventing respiratory diseases, such as COVID-19 and influenza, by interrupting viral transmission and safeguarding one's own health. In fact, researchers found that wearing masks can effectively reduce the infection rate of COVID-19 by 65%. However, this brings great inconvenience to face recognition, and human face recognition accuracy under occlusion conditions is low. Therefore, this paper proposes masked face recognition with BF-FaceNet and multi-view features. Firstly, in order to extract fine-grained features of the face region, ResNet50 is replaced by BoTNet as the backbone network of FaceNet. Secondly, a non-masked map is generated to accurately locate the non-masked area. Meanwhile, the face attention augmentation model (FAAM) is designed to extract local face features of the non-masked map. Thirdly, by combining loss function Ltriplet with Lattention, joint loss function Lface is proposed to improve the accuracy of masked recognition. Finally, experimental results on the publicly-available masked face dataset, SMFRD, demonstrate a significant improvement in recognition accuracy using our proposed algorithm compared to other methods.

show abstract

Section: Related Workmentioning

confidence: 99%

WITHDRAWN: Masked face recognition with BF-FaceNet and multi-view features

Sun

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We add this attention mechanism after each intermediate layer of a primary ResNet network, tune the model elements one by one to make them more accurate, and use this network as a backbone to build an FTM to compose our encoder [23]. Our encoder can thus extract the features of the input image compassionately.…”

Section: Psp-ganmentioning

confidence: 99%

The Application of 3D Virtual Technology in the Teaching of Clinical Medicine

Zhang

Kong

Yan

et al. 2022

Advances in Multimedia

View full text Add to dashboard Cite

The booming development of 3D virtual technology provides the basis for the innovation of teaching mode of clinical medicine. Integrating 3D virtual technology into the clinical education teaching of medical students can help medical students learn clinical expertise more intuitively, enrich practical experience, improve hands-on ability, and make up for the shortcomings of traditional medical teaching. However, the traditional 3D modeling method has the problems of sparse and insufficient accuracy of output results, which greatly limits the specific application of 3D virtual technology in clinical teaching. Therefore, this paper addresses the shortcomings of previous 3D virtual technology in 3D modeling of organs, introduces deep learning, and then proposes a pyramidal shape perception network with the ability to generate samples on point clouds. Experimental results show that the proposed model not only has a large improvement in accuracy but also shows a high degree of confidence in providing real-time feedback of local image attributes.

show abstract

“…In order to further alleviate the gradient disappearance or gradient explosion during the training of the adversarial network, the gradient penalty [14] is used to constrain GAN L :…”

Section: Multi-loss Fusion Optimization Methodsmentioning

confidence: 99%

Generative Adversarial Network Based on Multi-feature Fusion Strategy for Motion Image Deblurring

Jin¹,

Jin²

2022

Journal of Compurters

View full text Add to dashboard Cite

<p>Deblurring of motion images is a part of the field of image restoration. The deblurring of motion images is not only difficult to estimate the motion parameters, but also contains complex factors such as noise, which makes the deblurring algorithm more difficult. Image deblurring can be divided into two categories: one is the non-blind image deblurring with known fuzzy kernel, and the other is the blind image deblurring with unknown fuzzy kernel. The traditional motion image deblurring networks ignore the non-uniformity of motion blurred images and cannot effectively recover the high frequency details and remove artifacts. In this paper, we propose a new generative adversarial network based on multi-feature fusion strategy for motion image deblurring. An adaptive residual module composed of deformation convolution module and channel attention module is constructed in the generative network. Where, the deformation convolution module learns the shape variables of motion blurred image features, and can dynamically adjust the shape and size of the convolution kernel according to the deformation information of the image, thus improving the ability of the network to adapt to image deformation. The channel attention module adjusts the extracted deformation features to obtain more high-frequency features and enhance the texture details of the restored image. Experimental results on public available GOPRO dataset show that the proposed algorithm improves the peak signal-to-noise ratio (PSNR) and is able to reconstruct high quality images with rich texture details compared to other motion image deblurring methods.</p> <p> </p>

show abstract

A TextCNN and WGAN-gp based deep learning frame for unpaired text style transfer in multimedia services

Cited by 12 publications

References 19 publications

WITHDRAWN: Masked face recognition with BF-FaceNet and multi-view features

WITHDRAWN: Masked face recognition with BF-FaceNet and multi-view features

The Application of 3D Virtual Technology in the Teaching of Clinical Medicine

Generative Adversarial Network Based on Multi-feature Fusion Strategy for Motion Image Deblurring

Contact Info

Product

Resources

About