Day: Faster R-CNN

By fine tuning a mask R-CNN model trained in the PubLayNet, we can have a model that allows us to detect those parts of the documents that correspond to text. The model that we used is available in the Detectron2 platform, which is a platform from Facebook AI Research that allows fast tests of state of art algorithms.


  • Faster R-CNN and PEGASUS - Automatic text summarization in documents

    Faster R-CNN and PEGASUS - Automatic text summarization in documents

    Today, increasing volumes of documents and the information they contain must be...