Abstract
We present a model for saliency prediction in 360º videos based on the Transformer architecture. Our model leverages the global attention mechanism in order to represent the temporal dependencies that drive human attention. We compare our model with a current state-of-the-art model and outperform it for all metrics measured.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
