Counting the number of people in an image or video has attracted the attention of several researchers due to their increasing use in situations like video monitoring, public safety, crowd control, etc ...

In this paper, we present the graph attention auto-encoder (GATE), a neural network architecture for unsupervised representation learning on graph-structured data. Our architecture is able to ...

To perform the sanity check on the Decoder that was trained, the following sentences were run through the trained Decoder model, and the attention matrices were evaluated on the same sentences that ...

This model is based on a fully convolutional auto-encoder and can be trained end-to-end. It consists of two parts: encoder and decoder. The encoder and decoder are composed of convolutional layer ...

Auto-encoders are capable of performing input re-construction through an encoder-decoder structure. These net-works can serve many purposes such as noise removal and anomaly detection, whilst being ...