We proposed a convolutional autoencoder with sequential and channel attention (CAE-SCA) to address this issue. Sequential attention (SA) is based on long short-term memory (LSTM), which captures ...

The experimental results show that this method can effectively integrate the channel attention module and the fully convolutional autoencoder. Although it is an unsupervised feature learning model, it ...

In this work, we propose a Generative Convolutional Vision Transformer (GenConViT) for deepfake video detection. Our model combines ConvNeXt and Swin Transformer models for feature extraction, and it ...

QTCAE-IDS A quantised temporal convolutional autoencoder deployed on the PYNQ-Z2 FPGA using the FINN framework.

To overcome these limitations, a novel deep space-time generative graph convolutional autoencoder (SGGCA) is proposed. First, the PDS is modeled as a space-time graph where the nodes and edges show ...

Dachapally, P.R. (2017) Facial Emotion Detection Using Convolutional Neural Networks and Representational Autoencoder Units. arXiv 1706.01509.

A convolutional autoencoder processes RGB camera image input and extracts important spatial attention points.

To address these challenges, we propose EC2Vec, a multimodal autoencoder that embeds EC numbers in a meaningful and informative way. Our approach treats each digit in the EC number as a categorical ...

The convolutional autoencoder has a convolutional and deconvolutional layer that extracts hierarchical abstract features from the heart sound data, which not only reduces the dimensionality of the ...

A Convolutional Variational Autoencoder (CVAE) was developed for this purpose. We demonstrate the efficacy of our approach using the transient data generated from the simulations.