In this paper, we propose a video bitrate control method based on the quality and transfer data amount for WebRTC simulcast. Web conferencing services are typically controlled on the basis of quality of service, such as network bandwidth, jitter, and packet loss. However, these methods have two problems. First, they may provide excessive quality to users in network conditions where sufficient throughput is available. Providing excessive quality increases the amount of data transfer and operational costs. Second, WebRTC simulcast generally sets a fixed multiple bitrate, making it inflexible to user environment changes such as device type and small network throughput fluctuations. To solve these problems, we propose a video bitrate control method for WebRTC simulcast that reduces the amount of data transfer while achieving the required quality on the basis of device type, network condition, and quality of each user. The proposed method is implemented and evaluated under several conditions. This method can suppress the excess quality to control the bitrate on the basis of the quality considering the device type. In addition, it was also found that the bandwidth can be effectively utilized, and the quality can be improved by flexible bitrate control even in environments where the network fluctuates.

To improve users' experience and decrease their likelihood of quitting watching videos, this paper addresses the question of how to encode the videos used in adaptive bitrate (ABR) video streaming. When addressing ABR video streaming, a lot of effort has been put into developing ABR control schemes. However, ways to appropriately encode videos also need to be defined. Unlike previous approaches that focus on coding quality, this paper considers theuser quitting ratio. Theuser quitting ratiois the percentage of users still watching videos at a given time and enables us to address the consequences of quality and stimulus duration on the decision of a user to quit. Considering the value of theuser quitting ratio, this paper describes a method that uses content analysis, as well as a network's historical throughput data, to define how video should be encoded to decrease the likelihood of users quitting watching. Unlike previous approaches, the method is independent of the ABR control scheme used by the video player, and the selected ladders perform equivalently across different players with different behaviors. Results of experiments based on real-world network traces demonstrate the usefulness of the proposed method.

This paper addresses the improvement of the quality expe-rienced by users while using adaptive bitrate (ABR) video streaming by considering long-term aspects in the chunk se-lection process. Compared with traditional approaches that select chunks on the basis of predicted immediate throughput value, leveraging long-term throughput values can enable a long-term chunk selection strategy to be defined that enables perceived quality to be increased in challenging network con-ditions. In results for real-world throughput measurements, quality was improved by at least 0.5 units on a five-grade mean opinion score (MOS) in up to 60% of tested challenging network conditions thanks to the increase in the time frame in the chunk selection mechanism. Furthermore, using a long-term chunk selection mechanism was shown to enable higher quality to be maintained than short-term approaches when throughput prediction becomes noisy. The proposed approach was shown to benefit a quality-centric ABR control scheme but is also applicable to other ABR algorithms.

As adaptive bitrate streaming services are widely used, video streaming providers need to know what factors impact viewing abandonments. As quality and content-related factors are known to influence viewing abandonments, the reasons for viewing abandonments need to be analyzed while considering both factors. For this purpose, previous studies developed machine learning models, but most of them lack the interpretability of the relationships between explanatory variables and a target variable. In addition, causal relationships among explanatory variables need to be considered to disambiguate the effect of each variable. In this paper, we propose using Asymmetric Shapley value (ASV) to study the interpretability of a developed machine learning model and to take into account the effect of causalities among explanatory variables. We used a dataset collected in laboratory experiments on adaptive bitrate streaming and built binary classification models that classify viewing abandonment reasons into quality-induced or content-induced. We selected random forests as the best model and analyzed the relationships between explanatory variables (application quality, users' behavior, content attribute) and the target variable (viewing abandonment reason) with ASV. The results provided meaningful insights into the relationships and showed assuming causality is helpful to modify the estimation of the relationships

In this paper, a method is presented to estimate bitrate ladders on the basis of both content complexity and network traces. Unlike previous methods, the proposed algorithm is independent of the adaptive bitrate (ABR) control scheme used by the client. The proposed approach was evaluated in a simulation on the basis of real-life throughput measurements over a large period of time and across multiple ABR control schemes. Unlike in previous studies, perceptual quality metrics that account for the effect of both coding and stalling on video quality are used in the evaluations. Results show that the proposed method performs consistently over time and across ABR control schemes. Thus, this method will enable video streaming service providers to encode videos by using their knowledge of the network performance. This will ultimately enable network usage to be optimized and the quality of experience to be improved.

As video traffic volume increases, video streaming providers are struggling to improve the quality of experience (QoE). On the other hand, video viewers often prefer a lower traffic volume over a QoE that is too high since they contract for data-capped or pay-per-use communication plans. Thus, traffic volume should be reduced as much as possible while achieving the required QoE, which is the minimum QoE that will satisfy users. However, the required QoE depends on the context (e.g., the type of content and the preference of the user), and it is unrealistic and costly for users to set the required quality separately for each possible context. In this paper, we propose a context-aware adaptive bitrate streaming system that reduces the traffic volume while achieving the required QoE. Instead of requiring the required QoE to be configured by users, the proposed system uses the viewing time as implicit feedback on the QoE. By using this feedback, the proposed system automatically controls the QoE with a two-stage approach: it estimates the required QoE and calculates the bitrate to reduce the traffic volume while maintaining a QoE above the required QoE. To determine the required QoE based on few views, the proposed system searches for the required QoE in the mean opinion score space and uses Bayesian optimization. The results of trace-based simulations show that the proposed system can control the QoE close to the context-dependent required QoE based on fewer views than baseline algorithms.

In video-streaming services, adaptive bitrate (ABR) streaming is widely used, and service providers should monitor the quality of their services so that they can detect the quality degradation. Although many quality-estimation models have been developed for monitoring ABR streaming services, these models are insufficient for service providers. This is because, to improve their services after quality degrades, service providers need to know which quality-influencing features, such as audio bitrate, video representation (i.e., video bitrate, framerate, and resolution), and stalling, cause the degradation. In this paper, we propose a Shapley-value-based quality degradation analysis method to provide contribution values, which indicate the degree of quality degradation due to each quality-influencing feature for improving their services. The proposed method adapts the Shapley value concept to our problem and calculates the contribution values by comparing the estimated quality with the maximum quality, i.e., the quality of viewing history with the highest audio bitrates, highest quality level of video representation, and no stalling. In the evaluation, a viewing experiment dataset on ABR streaming is used, and results show that our proposed method can extract the quality-influencing feature that decreases quality the most by calculating contribution values.

Video streaming is an important application on the Internet. To ensure user satisfaction, video streaming service providers monitor their services in terms of quality and engagement. This enables them to ensure high quality services and grow their platform and incomes. However, studying user engagement is difficult as the decision of a user to quit or continue watching videos is jointly affected by many factors such as interest towards content, time available, and service quality. Therefore, the reason for quitting is difficult to identify. To address this, this study is based on usage data of a real-world TV service called Puffer and aims to study the relationship between service quality and quitting actions. Data from December 2020 were collected and correspond to 230,880 distinct viewing sessions. On the basis of these data, performing analysis at different scales (hour, day, month) enables the identification of different reasons for users to quit videos. By using this analysis, quality-related quitting events are identified and put into relation with quality-related parameters as well as state-of-the-art video quality and user quitting prediction models. Results show that quitting prediction models can be used to identify such events. Finally, by the means of logistic regression, this work describes the first steps towards mapping quitting prediction on the basis of models trained using data from laboratory experiments to real-world scenarios and shows a classification accuracy of 75.9%.

To improve user engagement such as viewing time, this paper addresses the understanding and prediction of theuser quitting ratiofor users watching videos using adaptive bit rate video streaming. Theuser quitting ratiois defined as the percentage of users still watching videos at a given time. To perform this study, five subjective experiments involving up to 264 participants were conducted in a laboratory setting. Results indicated the effects of coding quality, initial buffering, and midway stalling onuser quitting ratio. Then, a framework was defined to predict theuser quitting ratioas a function of time. This framework achieves good prediction accuracy and can be used in multiple scenarios including when quality adaptation and stalling occur. Finally, it is suitable for monitoring applications where bitstream are encrypted and low processing cost is required.

In this paper, a model is investigated for optimizing the encoding of adaptive bitrate video streaming. To this end, the relationship between quality, content duration, and acceptability measured by using the completion ratio is studied. This work is based on intensive subjective testing performed in a laboratory environment and shows the importance of stimulus duration in acceptance studies. A model to predict the completion ratio of videos is provided and shows good accuracy. By using this model, quality requirements can be derived on the basis of the target abandonment rate and content duration. This work will help video streaming providers to define suitable coding conditions when preparing content to be broadcast on their platform that will maintain user engagement.

As adaptive bitrate streaming services have spread, it has become more important for video streaming providers to control video quality and prevent viewing abandonments. However, since viewing abandonments are caused not only by quality degradations but also by a lack of users' interest in contents, it will first be necessary to clarify how quality and/or content affect viewing abandonments. To investigate this, we conducted an adaptive bitrate streaming experiment and developed a viewing-abandonment-reason-classification model that classifies abandonment reasons into quality or content. Using training data, we developed four models (logistic regression, classification tree, random forests, and support vector machine) where feature variables related to application quality, users' operation behaviors, and the attributes of viewed contents were used as explanatory variables. These four models were validated by using validation data. From the results, the support vector machine model was considered to be the best since it obtained relatively good validation results and did not appear to be over-trained.

In this study, the effect of coding degradation and stalling events on the percentage of users who quit watching videos midway is studied (referred to as the user quitting rate). The results are based on three laboratory-based subjective experiments involving up to 104 participants. The results show that for the coding condition only, a Mean Opinion Score (MOS) lower than 3 on a 5-point ACR quality scale will result in users quitting the video. The quitting rate was found to increase further when the MOS falls below 2.5. When a stalling event occurs, the quitting rate was found to be dependent on the stalling position, the stalling duration, the percentage of user who already quit, and the MOS. Statistical analysis allowed the identification of interaction terms between the stalling position and percentage of users who had already quit. Finally, the results were used to establish a model of the user quitting rate due to stalling.

Adaptive bitrate streaming services for mobile terminals have drastically spread in recent years, and it is becoming more important for service providers to increase users' satisfaction by understanding users' viewing behaviors (e.g., how long users watch videos, and why users quit viewing videos) and taking measures such as appropriately designing the quality levels of the videos to be placed on their distribution servers. To investigate the impacts of quality factors on users' viewing behaviors in adaptive bitrate streaming, we conducted an experiment in which participants could freely search and watch videos on smartphones under various network conditions. Through 800 10-minute tests, 1,449 valid views were collected, and the collected dataset was analyzed to characterize the impacts of the initial loading delay, average bitrate, and stalling events on the cumulative quit rate (CQR) of users. Furthermore, the impacts of the average bitrate and stalling events were evaluated quantitatively, using the 2-sample Anderson-Darling test, as well as the combined impact of these two quality factors. The characteristics of the impacts of the above quality factors indicate the possibility of applying survival analysis for our dataset, and suggest that the average bitrate, the number of stalling events, and the average stalling duration should be considered as the external covariates when building a model to estimate the users' viewing time.

In this work, the evaluation of user engagement's characteristics in adaptive bitrate video streaming is addressed. To this aim, the viewing time and its relation with video quality is studied in two carefully designed subjective tests. Video quality and viewing time were addressed in distinct experiments. In case of viewing time, users were allowed to stop watching the videos when they desired. It was found that for low-quality videos, the number of users dropping the video increases logarithmically as a function of time. In addition, when a stalling event occurs, users start dropping video playback after a waiting period of 5 seconds. Then, when the stalling ends, the dropping rate returns to its baseline rate (which depends on video quality). The number of users stopping watching video after a stalling event was found to be a function of stalling position, stalling duration, and the quality affected by coding. A baseline model considering only stalling features is defined. Finally, a model for predicting the video completion rate is proposed that achieves a Pearson correlation of 0.96 and a root-mean-square error (RMSE) of 0.064.

This paper describes an open dataset and software for ITU-T Ree. P.1203. As the first standardized Quality of Experience model for audiovisual HTTP Adaptive Streaming (HAS), it has been extensively trained and validated on over a thousand audiovisual sequences containing HAS-typical effects (such as stalling, coding artifacts, quality switches). Our dataset comprises four of the 30 official subjective databases at a bitstream feature level. The paper also includes subjective results and the model performance. Our software for the standard was made available to the public, too, and it is used for all the analyses presented. Among other previously unpublished details, we show the significant performance improvements of using bitstream-based models over metadata-based ones for video quality analysis, and the robustness of combining classical models with machine-learning-based approaches for estimating user QoE.

The use of adaptive-bitrate-streaming services over networks has been increasing in recent years. The quality of adaptive-bitrate-streaming services is primarily affected by the video resolution, the audio and video bitrate, bitrate adaptation, stalling due to a lack of playout buffer, and the content length. Therefore, service providers should monitor quality in real time to confirm the normality of their services. To accurately monitor quality, a model that can be used for quality estimation should be developed. To develop such a model, we first conducted extensive subjective quality assessment tests. We then developed a model using the subjective data obtained in the tests. Finally, we verified the performance of the proposed model by applying it to unknown datasets (different from the training datasets used to develop the model) and confirmed its high quality-estimation accuracy.

Significant progress has been made in the recent years in the development of technologies for encoders, decoders and networks. As a result, content, network, and Internet service providers can deliver video content over IP networks. To provide a high-quality service, the quality of experience (QoE) is becoming much more important. Since QoE is affected by such factors as the audiovisual content, encoding and decoding techniques, and network performance, service providers should monitor the QoE of a communication service in real time to confirm its status. To do this, a quality monitoring tool is necessary. The International Telecommunication Union - Telecommunication Standardization Sector Study Group 12 (ITU-T SG12) has studied the parametric non-intrusive assessment of audiovisual media streaming quality (P.NAMS). The P.NAMS - lower resolution application area was finally standardized as ITU-T Recommendation P.1201.1 in October 2012. The P.1201.1 model can be used for estimating audio, video, and audiovisual quality for mobile audiovisual media streaming using packet headers. Since the model analyzes only packet header information, the computational power of the model is very light, and the model can be applied to encrypted packets. This paper describes the P.1201.1 model and its performance.

Video quality improvement plays an important quality of experience (QoE) role in video application. In recent video distributions on the Internet, bitrate is changed automatically by using HTTP adaptive streaming (HAS). Bitrate change often depends on Internet bandwidth, display size, and memory buffer. In each bitrate, resolutions and frame rates can be selected freely. However, it is difficult to compare subjective video quality between different resolutions and frame rates. Therefore, we cannot determine the optimal resolution and frame rate that maximize subjective video quality. In this paper, we propose a method of estimating subjective video quality with various spatial and temporal resolutions. Our method does not need to encode videos for the most part, except for a few to estimate the relationship between bitrate and the quantization parameter (QP).

Multi-view coding is expected to be used in next-generation encoders and decoders for stereoscopic video services. In multi-view coding, the bit rate for the right eye view is lower than that for the left eye view because the right view is encoded using inter-view technology. In addition, the right view is encoded at a much lower bit rate on the basis of binocular suppression. As a result, the video quality for the left view can be different from that for the right view. We explore here how such a video quality difference between the left and right views affects the overall 3D video quality. In addition, we model the quality characteristics. We conducted a subjective quality assessment to derive subjective quality characteristics. We show that the difference in 2D video quality between the left and right views has little influence on the overall 3D video quality and that the overall 3D video quality can be modeled using the 2D video quality for left and right views.

We propose a no reference hybrid video-quality-estimation model for estimating video quality by using quality features derived from received packet headers and video signals. Our model is useful as a quality monitoring tool for estimating the video quality during use of an Internet protocol television service. It takes into account video quality dependence on video content and can estimate video quality per content, which our previously developed packet-layer model cannot do. We conducted subjective quality assessments to develop the model and validated its quality-estimation accuracy. The quality-estimation results showed that the Pearson-correlation coefficients were larger than 0.9 and the quality-estimation errors were equivalent to the statistical uncertainty of subjective quality.

IPTV services will become key services in the next- generation network (NGN). To provide a high-quality service for users, designing and managing the quality of experience (QoE) appropriately is extremely important. To do this, developing an objective quality-assessment method that estimates subjective quality based on physical characteristics of the IPTV system is desirable. We propose a parametric packet-layer model for monitoring video quality of IPTV services. Our proposed model is useful as a network monitoring tool for assessing several video parameters that affect the quality of IPTV services. For constructing the parametric packet-layer model, we derived a relationship between video quality and quality parameters from a subjective quality assessment. The results indicated that cross- correlation was larger than 0.9, and the evaluation error was smaller than the statistical uncertainty of the value of subjective quality. Therefore, our proposed model could be applied to effective design, implementation, and management of IPTV services.

IPTV services are attracting attention as an influential application of the next-generation network (NGN). Managing in-service communication quality based on users' quality of experience (QoE) is very important for improving customer satisfaction. For this, an accurate and efficient quality- assessment technology is desired. This is called objective quality assessment and has been studied for a long time. However, there are hardly any studies on methods that can be applied to quality monitoring at a user's premise. In this paper, we first overview the quality management approaches discussed in International Telecommunication Union (ITU). Next, we review available technologies from the viewpoint of the applicability to quality monitoring. Then, we propose a new objective quality-assessment approach to solve the problem current technologies have. To verify the validity of the new approach, we show a preliminary evaluation result of the proposed approach.

We present a multimedia quality integration function that can estimate the overall quality of a videophone service considering multimodality and interactivity. That is, it takes into account individual audiovisual qualities and their delays. Videophone services are rich multimedia services that are expected to become popular on the next-generation network (NGN). To provide ones with sufficient quality, we must properly evaluate, design, and manage users' perceptual quality of service, i.e., quality of experience (QoE). Subjective quality assessment tests were conducted using a PC-based point-to-point interactive videophone application to clarify how overall multimedia quality characteristics depend on the individual audiovisual qualities, absolute audiovisual delay, and media synchronization. From the test results, we formulated a multimedia quality integration function that can accurately evaluate overall multimedia quality. In addition, verification test results showed that this function achieved good performance in terms of correlation coefficient and evaluation error between subjective and estimated qualities. Our model will be a useful QoE planning tool capable of providing feedback on individual qualities as well as the overall multimedia quality of videophone services.

We propose a computational opinion model for estimating video quality of videophone services. Opinion models for speech such as the E-model have been established and widely used; however, little attention has been given to opinion models for video quality estimation. Our proposed opinion model is useful as a network-planning tool for assessing several video parameters that affect the quality of videophone services. First, we established a function for estimating video quality affected by coding degradation, which expresses the quality of a video affected by coding bit rate and frame rate. Second, we established a packet loss degradation index that estimates the degree of video quality degradation due to packet loss. Finally, we integrated these two functions into the opinion model for estimating video quality. We applied this model for video quality estimation of a videophone service with various video formats and displayed video sizes. The results indicated that the estimation errors of our model were less than the mean of the 99% confidence intervals for the subjective scores. Therefore, our model could be applied to effective design, implementation, and management of videophone applications and communication networks.