Learning Gaze Transitions from Depth to Improve Video Saliency Estimation

© 2017 IEEE. In this paper we introduce a novel Depth-Aware Video Saliency approach to predict human focus of attention when viewing videos that contain a depth map (RGBD) on a 2D screen. Saliency estimation in this scenario is highly important since in the near future 3D video content will be easil...

Full description

Bibliographic Details
Main Authors: Leifman, George (Author), Rudoy, Dmitry (Author), Swedish, Tristan (Author), Bayro-Corrochano, Eduardo (Author), Raskar, Ramesh (Author)
Other Authors: Massachusetts Institute of Technology. Media Laboratory (Contributor)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE), 2021-11-09T21:59:21Z.
Subjects:
Online Access:Get fulltext