Optimizing Fixation Prediction Using Recurrent Neural Networks for 360° Video Streaming in Head-Mounted Virtual Reality

Ching Ling Fan, Shou Cheng Yen, Chun Ying Huang, Cheng Hsin Hsu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

16 Scopus citations


We study the problem of predicting the viewing probability of different parts of 360° videos when streaming them to head-mounted displays. We propose a fixation prediction network based on recurrent neural network, which leverages sensor and content features. The content features are derived by computer vision (CV) algorithms, which may suffer from inferior performance due to various types of distortion caused by diverse 360° video projection models. We propose a unified approach with overlapping virtual viewports to eliminate such negative effects, and we evaluate our proposed solution using several CV algorithms, such as saliency detection, face detection, and object detection. We find that overlapping virtual viewports increase the performance of these existing CV algorithms that were not trained for 360° videos. We next fine-tune our fixation prediction network with diverse design options, including: 1) with or without overlapping virtual viewports, 2) with or without future content features, and 3) different feature sampling rates. We empirically choose the best fixation prediction network and use it in a 360° video streaming system. We conduct extensive trace-driven simulations with a large-scale dataset to quantify the performance of the 360° video streaming system with different fixation prediction algorithms. The results show that our proposed fixation prediction network outperforms other algorithms in several aspects, such as: 1) achieving comparable video quality (average gaps between-0.05 and 0.92 dB), 2) consuming much less bandwidth (average bandwidth reduction by up to 8 Mb/s), 3) reducing the rebuffering time (on average 40 s in bandwidth-limited 4G cellular networks), and 4) running in real-time (at most 124 ms).

Original languageEnglish
Article number8779683
Pages (from-to)744-759
Number of pages16
JournalIEEE Transactions on Multimedia
Issue number3
StatePublished - Mar 2020


  • 360° video
  • HMD
  • machine learning
  • prediction
  • RNN
  • tiled streaming
  • Virtual Reality


Dive into the research topics of 'Optimizing Fixation Prediction Using Recurrent Neural Networks for 360° Video Streaming in Head-Mounted Virtual Reality'. Together they form a unique fingerprint.

Cite this