Search Results - "Liu, Linwu"

Image super-resolution reconstruction based on feature map attention mechanism by Chen, Yuantao, Liu, Linwu, Phonevilay, Volachith, Gu, Ke, Xia, Runlong, Xie, Jingbo, Zhang, Qian, Yang, Kai

“…To improve the issue of low-frequency and high-frequency components from feature maps being treated equally in existing image super-resolution reconstruction…”
Get full text

Research on image Inpainting algorithm of improved GAN based on two-discriminations networks by Chen, Yuantao, Zhang, Haopeng, Liu, Linwu, Chen, Xi, Zhang, Qian, Yang, Kai, Xia, Runlong, Xie, Jingbo

“…All existing image inpainting methods based on neural network models are affected by structural distortions and blurred textures on visible connectivity, such…”
Get full text

Research on image inpainting algorithm of improved total variation minimization method by Chen, Yuantao, Zhang, Haopeng, Liu, Linwu, Tao, Jiajun, Zhang, Qian, Yang, Kai, Xia, Runlong, Xie, Jingbo

“…In order to solve the issue mismatching and structure disconnecting in exemplar-based image inpainting, an image completion algorithm based on improved total…”
Get full text

The image annotation algorithm using convolutional features from intermediate layer of deep learning by Chen, Yuantao, Liu, Linwu, Tao, Jiajun, Chen, Xi, Xia, Runlong, Zhang, Qian, Xiong, Jie, Yang, Kai, Xie, Jingbo

“…The automatic image annotation is an effective computer operation that predicts the annotation of an unknown image by automatically learning potential…”
Get full text

The improved image inpainting algorithm via encoder and similarity constraint by Chen, Yuantao, Liu, Linwu, Tao, Jiajun, Xia, Runlong, Zhang, Qian, Yang, Kai, Xiong, Jie, Chen, Xi

“…Existing image inpainting algorithms based on neural network models are affected by structural distortions and blurred textures on visible connectivity. As a…”
Get full text

Research of improving semantic image segmentation based on a feature fusion model by Chen, Yuantao, Tao, Jiajun, Liu, Linwu, Xiong, Jie, Xia, Runlong, Xie, Jingbo, Zhang, Qian, Yang, Kai

“…The context information of images had been lost due to the low resolution of features, and due to repeated combinations of max-pooling layer and down-sampling…”
Get full text