OrbitStream models semantic objects as sources of gravitational potential fields to predict operator gaze in 360 video without training and pairs it with a saturation-based PD controller for buffer control, reaching 94.7% zero-shot accuracy and second-best QoE in simulations.
Neural adaptive video stream- ing with pensieve
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
BG-CFQS provides risk-aware quantile-based forecasting for Starlink throughput that meets overestimation budgets and reduces positive errors compared to other feasible methods.
citing papers explorer
-
Training-Free Adaptive 360-degree Video Streaming via Semantic Potential Fields
OrbitStream models semantic objects as sources of gravitational potential fields to predict operator gaze in 360 video without training and pairs it with a saturation-based PD controller for buffer control, reaching 94.7% zero-shot accuracy and second-best QoE in simulations.