Fig 15 - uploaded by Miguel Romero
Content may be subject to copyright.
Download
View publication
Prediction error of CB-sal CVPR18-improved (with Content-Based saliency) against GT-sal CVPR18-improved (with Ground-Truth saliency) and baselines.

Prediction error of CB-sal CVPR18-improved (with Content-Based saliency) against GT-sal CVPR18-improved (with Ground-Truth saliency) and baselines.

Source publication
Fig. 1: 360 • video streaming principle. The user requests the next...
Fig. 2: For each time-stamp t, all the next positions from t until t +...
Fig. 15: Prediction error of CB-sal CVPR18-improved (with Content-Based...
Fig. 16: The dynamic head motion prediction problem cast as a...
Revisiting Deep Architectures for Head Motion Prediction in 360{\deg} Videos
Preprint
Full-text available
  • Nov 2019
Head motion prediction is an important problem with 360\degree\ videos, in particular to inform the streaming decisions. Various methods tackling this problem with deep neural networks have been proposed recently. In this article we first show the startling result that all such existing methods, which attempt to benefit both from the history of pas...
Cite
Download full-text

Similar publications

Complete figure of residual graph convolutional network block
Figure shows the encoder part of our deep augmented network
The proposed deep network architecture consists of GCN, linear...
Overview of the linear transformation incorporated discriminator...
Comparing the proposed method with two existing methods ([12], and...
Implicit regularization of a deep augmented neural network model for human motion prediction
Article
Full-text available
  • Jan 2023
Predicting human motion based on past observed motion is one of the challenging issues in computer vision and graphics. Existing research works are dealing with this issue by using discriminative models and showing the results for cases that follow a homogeneous distribution (in distribution) and not discussing the issues of the domain shift proble...
View