Deepqoe: A Unified Framework for Learning to Predict Video QoE

Zhang, Huaizheng; Hu, Han; Gao, Guanyu; Wen, Yonggang; Guan, Kyle

doi:10.1109/icme.2018.8486523

Cited by 25 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [33], thirteen QoS parameters were used for QoE prediction and the nearest neighbor approach was adopted due to the high-dimensionality of feature space. Owing to the outstanding ability of representation and prediction, some deep learning methods were successfully utilized for quality feature representation [34] and QoE prediction [35]. Moreover, some advanced machine learning methods such as boosting support vector regression [36] and adaptive network based fuzzy inference system (ANFIS) [37] were also utilized for QoE estimation.…”

Section: Estimation Model Based Methodsmentioning

confidence: 99%

Peripheral Sensing: Monitoring Quality of Experience for Video Services Based on Mobile Terminals

et al. 2019

View full text Add to dashboard Cite

Quality of experience (QoE), which directly relates to both technical evolvement and profit promotion, is a vital concern for mobile video services. However, the wireless network operators have long been troubled by the problem of lacking effective QoE monitoring approaches since the traditional evaluation methods of communication quality are objective metrics oriented. Considering that mobile terminals are the network elements closest to users, it is promising to realize a real-time QoE estimation for video services by fully utilizing the sensing capabilities of mobile terminals. As the first step, we specifically develop a mobile video testing application. With support from China Unicom, one of the three major wireless network operators in China, over 80 000 data records are collected under the real-world conditions. The collected data consist of four types of subjective scores and 13 objective parameters concerning video attributes, network performance, device capability, playback events, and external factors. After preprocessing the data set through correlation analysis, we establish the two QoE estimation models based on the C4.5 method and the gradient boosting decision tree (GBDT) method, respectively. The experimental results demonstrate that the proposed models can achieve remarkable estimation performances and outperform the baseline models. Specifically, the overall estimation accuracy of the GBDT-based model is approximately 80% for a five-level scale and approaches 90% when a more practical 3-level scale is adopted. Finally, we comprehensively discuss the estimation performances based on characteristics of the data and validate the feasibility of estimating QoE based on mobile terminals-the ''peripheral sensors'' of the mobile networks. INDEX TERMS Decision tree, mobile terminals, estimation model, QoE, video services.

show abstract

Section: Estimation Model Based Methodsmentioning

confidence: 99%

Peripheral Sensing: Monitoring Quality of Experience for Video Services Based on Mobile Terminals

et al. 2019

View full text Add to dashboard Cite

show abstract

“…There is also some work focusing on modeling QoE. E.g., [13,28] propose FM-liked QoE models; [29] uses a DNN-based models to characterize viewer engag ement. Our work differs with them as we further integrate the QoE method into the scheduling problem.…”

Section: Related Workmentioning

confidence: 99%

Leveraging QoE Heterogenity for Large-Scale Livecaset Scheduling

Zhang

Huang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Livecast streaming has received great success in recent years. Although many prior efforts have suggested that dynamic viewer scheduling according to the quality of service (QoS) can improve user engagement, they may suffer inefficiency due to their ignorance of viewer heterogeneity in how the QoS impact quality of experience (QoE). In this paper, we conduct measurement studies over large-scale data provided by a top livecast platform in China. We observe that QoE is influenced by a lot of QoS and non-QoS factors, and most importantly, the QoE sensitivity to QoS metrics can vary significantly among viewers. Inspired by the above insights, we propose HeteroCast, a novel livecast scheduling framework for intelligent viewer scheduling based on viewer heterogeneity. In detail, Hetero-Cast addresses this concern by solving two sub-problems. For the first sub-problem (i.e., the QoE modeling problem), we use the deep factorization machine (DeepFM) based method to precisely map complicated factors (QoS and non-QoS factors) to QoE and build the QoE model. For the second sub-problem (i.e., the QoE-aware scheduling problem), we use a graph-matching method to generate the best viewer allocation policy for each CDN provider. Specifically, by using some pruning techniques, HeteroCast only introduces slight overhead and can well adapt to the large-scale livecast scenario. Through extensive evaluation on real-world traces, HeteroCast is demonstrated to increase the average QoE by 8.87%-10.09%. CCS CONCEPTS • Information systems → Multimedia streaming; • Computing methodologies → Neural networks.

show abstract

“…Zhang et al [47] explored a framework for predicting the video QoE based on machine learning, called DEEPQoE. Figure.…”

Section: Jnd Application In Perceptual Quality Assessmentmentioning

confidence: 99%

Visual JND: A Perceptual Measurement in Video Coding

Zhao

Xue

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Humans cannot perceive the minimal level of difference in the pixel variation. To overcome the problem, the concept of just-noticeable difference (JND) was proposed. JND measures the minimal amount that must be changed for the variation to be detectable by humans. However, JND characteristics were not considered in the traditional perceptual measurements. In this paper, we provide a comprehensive survey of the latest JND-related studies. First, we provide an extensive overview of JND models. JND models comprise human visual system characteristics and masking effects. Next, we introduce the applications of JND models in the perceptual quality evaluation and video compression coding, especially in applying machine-learning techniques to JND prediction. In addition to a thorough summary of the recent progress and applications of JND, we summarize some unsolved technical challenges. We believe that our overview and findings can provide some insights into the related issues and future research directions in video coding. INDEX TERMS Just noticeable difference (JND), human visual system (HVS), machine learning, perceptual measurement, video coding.

show abstract

Deepqoe: A Unified Framework for Learning to Predict Video QoE

Cited by 25 publications

References 21 publications

Peripheral Sensing: Monitoring Quality of Experience for Video Services Based on Mobile Terminals

Peripheral Sensing: Monitoring Quality of Experience for Video Services Based on Mobile Terminals

Leveraging QoE Heterogenity for Large-Scale Livecaset Scheduling

Visual JND: A Perceptual Measurement in Video Coding

Contact Info

Product

Resources

About