Evaluating Quality of Experience for Streaming Video in Real Time
The authors present a scalable, lightweight, no-reference framework to infer video QoE. Their framework revolves around a onetime offline construction of a k-dimensional space, which they call the QoE space. The k-dimensions accommodate k parameters (network-dependent/independent) that potentially affect video quality. The k-dimensional space is partitioned to N representative zones, each with a QoE index. Instantaneous parameter values are matched with the indices to infer QoE. To validate their framework, they construct a 3-dimensional QoE space with bit-rate, loss, and delay as the principal components.