Suchergebnisse - dilated encoder–decoder ConvLSTM

PDED-ConvLSTM: Pyramid Dilated Deeper Encoder–Decoder Convolutional LSTM for Arctic Sea Ice Concentration Prediction von Zhang, Deyu, Wang, Changying, Huang, Baoxiang, Ren, Jing, Zhao, Junli, Hou, Guojia

“… To address these challenges, we propose an innovative encoder–decoder pyramid dilated convolutional long short-term memory network (DED-ConvLSTM …”
Volltext

Multi-Scale Attention and Encoder-Decoder Network for Video Saliency Object Detection von Bi, Hongbo, Zhu, Huihui, Yang, Lina, Wu, Ranwan

“… : spatial module and temporal module. In spatial module: we use a set of parallel dilated convolutions, and add channel attention to each dilated convolutions …”
Volltext

Short-Term Load Forecasting Using Encoder-Decoder WaveNet: Application to the French Grid von Dorado Rueda, Fernando, Durán Suárez, Jaime, del Real Torres, Alejandro

“… To this end, the authors propose an encoder-decoder architecture inspired by WaveNet, a deep generative model initially designed by Google DeepMind for raw audio waveforms …”
Volltext

D2CL: A Dense Dilated Convolutional LSTM Model for Sea Surface Temperature Prediction von Hou, Siyun, Li, Wengen, Liu, Tianying, Zhou, Shuigeng, Guan, Jihong, Qin, Rufu, Wang, Zhenfeng

“… In this work, we proposed a novel dense dilated convolutional LSTM (D2CL) model to predict SST …”
Volltext

多层次特征融合与超图卷积的生成对抗壁画修复 von 陈永, 陶美风, 赵梦雪

“… 及门控机制融合多分支特征方法,将相邻分支间的特征信息进行融合,使融合后的壁画特征图中既有同分支的特征,又有相邻分支的特征,以提高特征信息的利用率;并引入门控机制对特征进行选择融合,以减少细节信息的丢失.接着,将融合特征通过卷积长短期记忆网络(ConvLSTM)特征注意力方法,增强对壁画上下文信息的关注.最后,设计超图卷积 …”
Volltext

An integrated deep learning framework for joint segmentation of blood pool and myocardium von Du, Xiuquan, Song, Yuhui, Liu, Yueguo, Zhang, Yanping, Liu, Heng, Chen, Bo, Li, Shuo

“… such as inception module, dilated convolution, and ConvLSTM module are used to assist the residual network …”
Volltext