A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Subtitle-based Viewport Prediction for 360-degree Virtual Tourism Video
[article]
2022
arXiv
pre-print
Preserved Fulltext
Therefore, in this paper, a subtitle-based viewport prediction model for 360-degree virtual tourism videos is proposed. ...
360-degree streaming videos can provide a rich immersive experiences to the users. However, it requires an extremely high bandwidth network. ...
The obtained ground-truth saliency heat map are input to a CNN network to extract a saliency feature vector f (t) GT S which will be used for viewport prediction in the proposed model.
B. ...
arXiv:2206.02367v1
fatcat:xfiy6kwvxrflbpbiq6sew2jwum
Gaze Prediction in Dynamic 360° Immersive Videos
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Then we feed both the saliency maps and the corresponding images into a Convolutional Neural Network (CNN) for feature extraction. ...
Extensive experiments validate the effectiveness of our method for gaze prediction in dynamic VR scenes. * Corresponding author ing problem in 360 • videos, from both the commercial and technology perspectives ...
for better saliency prediction. ...
doi:10.1109/cvpr.2018.00559
dblp:conf/cvpr/XuDWSSYG18
fatcat:ix36vmyf3rbrne4d6iwp5wkcgy
Saliency Detection in 360$$^\circ $$∘ Videos
[chapter]
2018
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
This paper presents a novel spherical convolutional neural network based scheme for saliency detection for 360 • videos. ...
Comprehensive experiments validate the effectiveness of our spherical U-net for 360 • video saliency detection. ...
There still exists some space to improve our method for video saliency prediction. ...
doi:10.1007/978-3-030-01234-2_30
fatcat:4q6kqlxqm5hy5mhjscwhr2yeu4
ATSal: An Attention Based Architecture for Saliency Prediction in 360 Videos
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Accordingly, researchers have proposed various saliency models for 360 video/images. This paper proposes ATSal, a novel attention based (head-eye) saliency model for 360\degree videos. ...
The spherical domain representation of 360 video/image presents many challenges related to the storage, processing, transmission and rendering of omnidirectional videos (ODV). ...
publication has emanated from research supported by Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289 P2, co-funded by the European Regional Development Fund, through the SFI Centre for ...
arXiv:2011.10600v1
fatcat:wes6y4glqrdcfdaos6nluhti5i
Cube Padding for Weakly-Supervised Saliency Prediction in 360 Videos
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Automatic saliency prediction in 360 videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). ...
To evaluate our method, we propose Wild-360, a new 360 video saliency dataset, containing challenging videos with saliency heatmap annotations. ...
Acknowledgements We thank MOST-106-3114-E-007-008 and MediaTek for their support. ...
arXiv:1806.01320v1
fatcat:dbrcy25zzrft5efopsr3ua2ble
Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Automatic saliency prediction in 360 • videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). ...
To evaluate our method, we propose Wild-360, a new 360 • video saliency dataset, containing challenging videos with saliency heatmap annotations. ...
Acknowledgements We thank MOST-106-3114-E-007-008 and MediaTek for their support. ...
doi:10.1109/cvpr.2018.00154
dblp:conf/cvpr/ChengCDWLS18
fatcat:swpeogbh6nc43fi3ikeu4wpxp4
Deep reinforcement learning approach to predict head movement in 360° videos
2022
IS&T International Symposium on Electronic Imaging Science and Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Therefore, in this proposed network we utilise a saliency indicator for driving the reward function of the reinforcement learning framework. ...
In addition to this, saliency estimation is proved to be a very powerful indicator for attention modelling. ...
Acknowledgments We would like to thank IIIT Vadodara for providing access to the Param Shavak server, which is a facility provided by the Gujarat Council on Science and Technology, India.
367-4 IS&T ...
doi:10.2352/ei.2022.34.10.ipas-367
fatcat:4ikh5hrtufbdfktpl7tn54m7wu
QoE-Oriented Resource Allocation for 360-degree Video Transmission over Heterogeneous Networks
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Besides, a novel buffer strategy is proposed to mitigate the influence of short-time prediction problem for transmitting 360-degree videos in time-varying networks. ...
in 360-degree video streaming. ...
However, as illustrated in Section I, buffer management schemes for traditional videos are not appropriate for 360-degree videos due to the short-time prediction nature of FoV. ...
arXiv:1803.07789v1
fatcat:tdgznm6m2ra2rjjt22hnehnp7a
Adaptive Panoramic Video Multicast Streaming with Limited FoV Feedback
2020
Complexity
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Then, we design a QoE-driven panoramic video streaming system with a client/server (C/S) architecture, in which the server performs rate adaptation based on the bandwidth and the predicted FoV. ...
Virtual reality (VR) provides an immersive 360-degree viewing experience and has been widely used in many areas. ...
Acknowledgments is research was supported in part by the Fundamental Research Funds for the Central Universities, under Grant nos. JZ2019HGTB0089 and PA2020GDJQ0027. ...
doi:10.1155/2020/8832715
fatcat:hogx3l7h4rdmtka5eyqwp4gs4q
HSMF-Net: Semantic Viewport Prediction for Immersive Telepresence and On-Demand 360-degree Video
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
An on-demand 360-degree video streaming framework is presented to prove its general validity. ...
The proposed approach increases the perceived video quality while requiring a significantly lower transmission rate. ...
Proper viewport (or HM) prediction is needed for immersive user experience both for live telepresence and on-demand 360 • video streaming. ...
arXiv:2009.04015v1
fatcat:exl7xwt2hzaaxjg6b3a34zoiw4
A unified evaluation framework for head motion prediction methods in 360° videos
2020
Proceedings of the 11th ACM Multimedia Systems Conference
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The streaming transmissions of 360°videos is a major challenge for the development of Virtual Reality, and require a reliable head motion predictor to identify which region of the sphere to send in high ...
We also provide the description of the algorithms used to compute the saliency maps either estimated from the raw video content or from the users' statistics. ...
Owing to this acute need for head motion prediction in 360°video streaming, a number of recent approaches have proposed deep neural networks meant to exploit the knowledge of the past positions and of ...
doi:10.1145/3339825.3394934
dblp:conf/mmsys/Romero-RondonSA20
fatcat:wkqpzje3mvd55h2ixz4rsbh3mi
Encoder-Decoder Based LSTM Model to Advance User QoE in 360-Degree Video
2022
Computers Materials & Continua
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Then, this prediction model is combined with a rate adaptation approach that assigns the bitrates to various tiles for 360-degree video frames under a given network capacity. ...
The development of multimedia content has resulted in a massive increase in network traffic for video streaming. ...
Acknowledgement: We would like to thank all reviewers for reviewing and giving valuable comments to improve the manuscript's quality. ...
doi:10.32604/cmc.2022.022236
fatcat:4vczirpgn5dl5dqwnwtcl736mi
State-of-the-art in 360 Video/Image Processing: Perception, Assessment and Compression
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
First, this paper reviews both datasets and visual attention modelling approaches for 360 video/image. ...
The spherical viewing range of 360 video/image accounts for huge data, which pose the challenges to 360 video/image processing in solving the bottleneck of storage, transmission, etc. ...
[18] , such that the PanoSalNet approach can be used for 360°video saliency prediction. ...
arXiv:1905.00161v2
fatcat:uom7choft5h47gj6fdr66wlooa
Analysis of Object-Centric Visual Preference in 360-degree Videos
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
After defining the static and dynamic properties of the objects of interest, we collect real-shot 360-degree videos and synthesize computer-generated 360-degree videos so that the objects have different ...
by detecting and comparing static and dynamic properties of objects in a 360-degree video. ...
VISUAL SALIENCY PREDICTION FOR 360-DEGREE IMAGES/VIDEOS Several studies have recently been performed to predict visual saliency maps for 360-degree images and videos [8] - [12] . ...
doi:10.1109/access.2021.3095284
fatcat:yh7n5ho5afekjfbkivn6tmfcfm
Functional gaze prediction in egocentric video
2020
Proceedings of the 18th International Conference on Advances in Mobile Computing & Multimedia
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Streaming 360°videos to a head-mounted display (HMD) client is challenging due to their high network resource consumption and computational load. ...
We propose a functional gaze prediction system that addresses these issues by relying on a tiling scheme for gaze prediction. ...
ACKNOWLEDGMENTS The authors appreciate partial funding from Nokia Solutions and Networks. ...
doi:10.1145/3428690.3429174
fatcat:xvcrbjzcnffotjyb3ywztgvm6e
« Previous
Showing results 1 — 15 out of 2,348 results