Accurate long-term viewport prediction in tile-based 360° video adaptive streaming helps pre-download tiles for a further future, thus establishing a longer buffer to cope with network fluctuations. Long-term viewport motion is mainly influenced by Historical viewpoint Trajectory (HT) and Video Content information (VC). However, HT and VC are difficult to align in space due to their different modalities, and their relative importance in viewport prediction varies across prediction time steps. In this paper, we propose STAR-VP, a model that fuses HT and VC in a Space-aligned and Time-vARying manner for Viewport Prediction. Specifically, we first propose a novel saliency representation salxyz and a Spatial Attention Module to solve the spatial alignment of HT and VC. Then, we propose a two-stage fusion approach based on Transformer and gating mechanisms to capture their time-varying importance. Visualization of attention scores intuitively demonstrates STAR-VP's capability in space-aligned and time-varying fusion. Evaluation on three public datasets shows that STAR-VP achieves state-of-the-art accuracy for long-term (2-5s) viewport prediction without sacrificing short-term (<1s) prediction performance.

In the field of 360-degree video streaming, the optimization of visual quality within the viewer's field of view, alongside the minimization of system resource consumption, is a critical concern. The considerable file sizes associated with high-quality 360-degree videos pose significant challenges for efficient transmission. Current strategies primarily employ a tile-based approach to address these issues. However, these approaches face two core challenges: the methodology for tile segmentation, and the strategy for downloading tiles. To address these challenges, this paper presents a tile-based solution designed specifically for adaptive 360-degree video-on-demand streaming. Our method surpasses baseline methods in extensive simulations, positioning it as one of the leading solutions in the MMSys'24 Grand Challenge1.