Kuniaki Saito

Learn More
Visual question answering (VQA) task not only bridges the gap between images and language, but also requires that specific contents within the image are understood as indicated by linguistic context of the question, in order to generate the accurate answers. Thus, it is critical to build an efficient embedding of images and texts. We implement DualNet,(More)
Hu proteins are RNA-binding proteins that are the vertebrate homologs of Drosophila ELAV, and are implicated in stabilization or enhanced translation of specific mRNAs with AU-rich elements (AREs) in the 3'-untranslated region. Here, using the yeast two-hybrid system, we show that neuron-specific Hu proteins can interact with themselves. Immuno(More)
RNA-binding proteins (RBPs) play a vital role in the post-transcriptional regulation of gene expression during neuronal differentiation and synaptic plasticity. One such RBP family, the neuronal Hu protein family, serves as an early marker of neuronal differentiation and targets several mRNAs containing adenine/uridine-rich elements. Recently, we reported(More)
Obtaining common representations from different modalities is important in that they are interchangeable with each other in a classification problem. For example, we can train a classifier on image features in the common representations and apply it to the testing of the text features in the representations. Existing multi-modal representation learning(More)
  • 1