News

IEEE1d
Attention-Based Feature Fusion Empowered Encoder-Decoder Framework for Nighttime Traffic Perception From High-Altitude Surveillance System
In this study, we propose a novel lightweight model specifically for reliable traffic perception in low-light conditions, utilizing an encoder-decoder architecture ... deep two-channel neural network ...
IEEE27d
Improved Encoder-Decoder Architecture With Human-Like Perception Attention for Monaural Speech Enhancement
Abstract: Speech enhancement (SE) models based on deep neural networks ... a high-efficiency encoder-decoder structure, inspired by the top-down attention mechanism in human brain perception and named ...
Frontiers21d
Association prediction of lncRNAs and diseases using multiview graph convolution neural network
MVIGCN model is a neural network model of codec structure, as shown in Figure 1, which mainly includes two parts: encoder part and decoder part. In this paper, the encoder was used to extract ...
Frontiers19d
Synthesizing intelligible utterances from EEG of imagined speech
Decoding natural language directly from neural activity is of great interest ... an empirically determined loss threshold. Figure 4. Network structure diagram of the XI model. It consists of two ...
GitHub24d
MEDCNN: Multiresolution Encoder-Decoder Convolutional Neural Network
This is a 2D version of MEDCNN and without attentions in the decoder Full paper with attentions: https://doi.org/10.1109/ICASSP49660.2025.10890832 ...
Intelligent neural network model enhances space reactor shielding design
Researchers from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences have developed a neural network model based on self-attention mechanisms to rapidly predict radiation ...