Category: 7. Maths

Continue Reading

  • Viewport prediction with cross modal multiscale transformer for 360° video streaming

    Viewport prediction with cross modal multiscale transformer for 360° video streaming

    The architecture of our Cross Modal Multiscale Transformer (CMMST) is illustrated in Fig. 4. Our model takes as input both the saliency map and the user’s trajectory, embedding each into a unified vector space compatible with the Transformer…

    Continue Reading