Marc Masana

Learn More
This paper presents the systems developed by LIUM and CVC for the WMT16 Mul-timodal Machine Translation challenge. We explored various comparative methods , namely phrase-based systems and at-tentional recurrent neural networks models trained using monomodal or multi-modal data. We also performed a human evaluation in order to estimate the usefulness of(More)
Object detection with deep neural networks is often performed by passing a few thousand candidate bounding boxes through a deep neural network for each image. These bounding boxes are highly correlated since they originate from the same image. In this paper we investigate how to exploit feature occurrence at the image scale to prune the neural network which(More)
  • 1