Proceedings of the 27th ACM International Conference on Multimedia 2019
DOI: 10.1145/3343031.3350601
|View full text |Cite
|
Sign up to set email alerts
|

User-Adaptive Editing for 360 degree Video Streaming with Deep Reinforcement Learning

Abstract: The development through streaming of 360°videos is persistently hindered by how much bandwidth they require. Adapting spatially the quality of the sphere to the user's Field of View (FoV) lowers the data rate but requires to keep the playback buffer small, to predict the user's motion or to make replacements to keep the buffered qualities up to date with the moving FoV, all three being uncertain and risky. We have previously shown that opportunistically regaining control on the FoV with active attention-drivin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

1
0
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(1 citation statement)
references
References 11 publications
1
0
0
Order By: Relevance
“…For the aligned group we observe that FR 40 has the lower mean: 8% lower than snapcut, followed by FR 60 • with 2.46% lower than snap-cut, the total mean head speed reduction was FR 10 • = 14.9 • , FR 20 • = 9.5, FR 40 • = 26.7 • , FR 60 • =33.1 • , Snap-cut = 21.5 • . A common consequence between all edit types tested is that they affected reducing head speed, which may be related to the fixation at ROI, reducing the exploratory behavior, this stability effect agrees with the literature [79] and can be useful for streaming applications. As a remark, for this analysis we filtering head speed higher than 150 • /s (refer to Section IV-C3 for description).…”
Section: Analysis Of Head Motion Metricssupporting
confidence: 86%
“…For the aligned group we observe that FR 40 has the lower mean: 8% lower than snapcut, followed by FR 60 • with 2.46% lower than snap-cut, the total mean head speed reduction was FR 10 • = 14.9 • , FR 20 • = 9.5, FR 40 • = 26.7 • , FR 60 • =33.1 • , Snap-cut = 21.5 • . A common consequence between all edit types tested is that they affected reducing head speed, which may be related to the fixation at ROI, reducing the exploratory behavior, this stability effect agrees with the literature [79] and can be useful for streaming applications. As a remark, for this analysis we filtering head speed higher than 150 • /s (refer to Section IV-C3 for description).…”
Section: Analysis Of Head Motion Metricssupporting
confidence: 86%