We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...

Abstract: Recent deep learning methods for vessel trajectory prediction are able to learn complex maritime patterns from historical automatic identification system (AIS) data and accurately predict ...

You can see the live demos at the following links. You can also access the styles as JSON for testing in mobile or other style tools. This is the sample vector map displayed on the frontpage of https: ...

Abstract: Deep-learning-based watermarking technique is being extensively studied. Most existing approaches adopt a similar encoder-driven scheme which we name END (Encoder-NoiseLayer-Decoder) ...