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: Change detection is a critical task in earth observation applications. Recently, deep-learning-based methods have shown promising performance and are quickly adopted in change detection.

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 ...

To download the pre-generated dataset used in our paper, please run the following command: We then benchmark the decoding quality and perplexity of those decoding methods. Please check the Benchmark ...