Predicting 360° Video Saliency: A ConvLSTM Encoder-Decoder Network With Spatio-Temporal Consistency

360° videos have been widely used with the development of virtual reality technology and triggered a demand to determine the most visually attractive objects in them, aka 360° video saliency prediction (VSP). While generative models, i.e., variational autoencoders or autoregressive models have prove...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal on emerging and selected topics in circuits and systems Vol. 14; no. 2; pp. 311 - 322
Main Authors: Wan, Zhaolin, Qin, Han, Xiong, Ruiqin, Li, Zhiyang, Fan, Xiaopeng, Zhao, Debin
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.06.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
360° videos
Active appearance model
Autoregressive models
Circuits and systems
Computer architecture
Convolutional neural networks
Distortion
Effectiveness
Encoders-Decoders
Feature extraction
Gaussian priors
Modules
Salience
Saliency prediction
Solid modeling
spatio-temporal features
Spatiotemporal data
Video
Virtual reality
ISSN:2156-3357, 2156-3365
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:360° videos have been widely used with the development of virtual reality technology and triggered a demand to determine the most visually attractive objects in them, aka 360° video saliency prediction (VSP). While generative models, i.e., variational autoencoders or autoregressive models have proved their effectiveness in handling spatio-temporal data, utilizing them in 360° VSP is still challenging due to the problem of severe distortion and feature alignment inconsistency. In this study, we propose a novel spatio-temporal consistency generative network for 360° VSP. A dual-stream encoder-decoder architecture is adopted to process the forward and backward frame sequences of 360° videos simultaneously. Moreover, a deep autoregressive module termed as axial-attention based spherical ConvLSTM is designed in the encoder to memorize features with global-range spatial and temporal dependencies. Finally, motivated by the bias phenomenon in human viewing behavior, a temporal-convolutional Gaussian prior module is introduced to further improve the accuracy of the saliency prediction. Extensive experiments are conducted to evaluate our model and the state-of-the-art competitors, demonstrating that our model has achieved the best performance on the databases of PVS-HM and VR-Eyetracking.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2156-3357
2156-3365
DOI:10.1109/JETCAS.2024.3377096