Understanding the impact of video quality on user engagement

By Florin Dobrian, Vyas Sekar, Asad Awan, Ion Stoica, D. Joseph, Aditya Ganjam, Jibin Zhan, Hui Zhang. Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication, 2011

871 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/22bd3a35b9550bc5b570a0beee5648eb9033be3b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Oboe: auto-tuning video ABR algorithms to network conditions (2018, background): “Average bitrate and rebuffering ratio were found to have the most impact on user quality of experience [23], though other factors such as changes in bitrates during a session can play a role [23].”
BOLA: Near-optimal bitrate adaptation for online videos (2016, background): “…that start slowly, play at lower bitrates, and freeze frequently can cause viewers to abandon the videos or watch fewer minutes of the videos, signiﬁcantly decreasing the opportunity for generating revenue for the video providers [2]–[4], underscoring the need for a high-quality user experience.”
PCC Vivace: Online-Learning Congestion Control (2018, methodology): “We compare the streamed video’s buffering ratio [10], calculated as the ratio of time spent during buffering relative to total streaming session time, using Vivace-Latency, AllegroLatency, BBR, and TCP CUBIC.”
Understanding the impact of network dynamics on mobile video user engagement (2014, background): “The initial modality in the distribution indicates abandonment that is likely either because users tend to sample videos [7] or due to longer join times [9].”
this paper (2009, background): “We further measure the smoothness of frame-rate, which might also have potential effects on users’ experiences [33].”
CS2P: Improving Video Bitrate Selection and Adaptation with Data-Driven Throughput Prediction (2016, methodology): “Delivering good application-level video quality-of-experience (QoE) entails new metrics such as low buffering or smooth bitrate delivery [5, 22].”
Video stream quality impacts viewer behavior: inferring causality using quasi-experimental designs (2012, background): “However, it must be noted that [9] studies a larger set of quality metrics, including join time, average bitrate, and rendering quality, and a larger class of videos including live streaming, albeit without establishing causality.”
Improving fairness, efficiency, and stability in HTTP-based adaptive video streaming with FESTIVE (2012, background): “The player tries to maintain an adequate video playback buffer to minimize rebuffer-ing which can adversely impact user engagement [21].”
Probe and Adapt: Rate Adaptation for HTTP Video Streaming At Scale (2013, background): “Empirical study [9] has shown that buffer underrun may have the most severe impact on a user’s viewing experience.”
Confused, timid, and unstable: picking a video streaming rate is hard (2012, background): “According to the latest Consumer Reports [21], Netﬂix is the most popular video streaming provider in the United States, while The video rates available from each of the three services are summarized in Table 2; some playback rates may not be available for some videos.”
A buffer-based approach to rate adaptation (2014, methodology): “The design goal of an ABR algorithm is to simultaneously obtain high performance on both metrics in order to give users a good viewing experience [7].”
Developing a predictive model of quality of experience for internet video (2013, methodology): “The data used in this paper was collected by conviva.com in real time using a client-side instrumentation library.”
From QoS to QoE: A Tutorial on Video Quality Assessment (2015, methodology): “In [48], a framework is built for identifying QoS metrics that have signiﬁcant impact on user QoE for different video types; and quantifying such inﬂuence by linear regression.”
Neural Adaptive Video Streaming with Pensieve (2017, background): “Many studies have shown that users will quickly abandon video sessions if the quality is not sufﬁcient, leading to signiﬁcant losses in revenue for content providers [12, 25].”