A Framework for Multi-Task Learning in Dynamic Adaptive Streaming Over HTTP

Abstract

This paper presents a framework with a taxonomy for multi-task learning in the context of Dynamic Adaptive Streaming over HTTP (DASH). DASH is a widely used technology for video streaming, and multi-task learning has emerged as a promising approach to enhance the performance and user experience of DASH systems by jointly optimizing multiple related tasks. The framework provides a structured approach to design, train, and evaluate multi-task learning models in DASH, while the taxonomy categorizes the key components and approaches within the framework. The taxonomy includes task types, multitask learning approaches, input features, and training strategies. Task types encompass video quality adaptation, buffer management, bandwidth estimation, content pre-fetching, and resource allocation, representing the specific tasks involved in DASH. Multi-task learning approaches encompass methodologies such as shared representation learning, task-specific layers, multi-head architectures, knowledge distillation, and reinforcement learning, offering flexibility in model design and optimization. Input features cover video characteristics, network conditions, device capabilities, and user preferences, providing the necessary information for informed decision-making across tasks. Training strategies include joint training, alternate training, hierarchical training, task weighting, and task balancing, determining how the multi-task learning model is trained and optimized. By following the presented framework and taxonomy, researchers and practitioners can systematically approach the design, training, and evaluation of multi-task learning models in DASH. The framework enables the development of efficient and adaptive video streaming systems by leveraging the interdependencies among tasks. The taxonomy helps organize the components and approaches within the framework, aiding in a better understanding of the various aspects of multi-task learning in the DASH context. Overall, this framework and taxonomy provide a valuable resource for advancing the field of multitask learning in the dynamic and complex domain of video streaming over HTTP.

Authors and Affiliations

Koffka Khan

Keywords

Related Articles

Protection of Bank Customers in Savings Account Hacking Through Illegal Links

Research regarding the protection of bank customers in savings account hacking through illegal links aims to determine legal protection for bank customers who are victims of burglary of savings accounts via illegal links...

Constructing A Model of Factors Affecting the Effectiveness of Internal Auditors at Public Non-Business Units in Vietnam

The article presented the concepts of internal auditors, public non-business units and some related concepts. In order to meet the goal of constructing a model of factors affecting internal audit effectiveness, the resea...

Ave Satani Motifs Relation to Narrative Thematic Development of the Omen: An Analysis of Oscar-Winning Horror Film Music

It is noteworthy to distinguish the excellence of Ave Satani’s theme song for The Omen (1976) film so that it becomes the only horror movie that ever won a nomination for "Best Original Song" over the ninety years of the...

The Effect of Economic Growth, Local Original Revenue, General Allocation Fund, Special Allocation Fund, and Profit Sharing Fund on Capital Expenditure of The NTB Provincial Government

The authority and policy of regional autonomy is carried out by the regional government. Local governments can facilitate economic growth and regional development, reduce community inequality, and advance community servi...

Modern Management Inteligence Competitive Strategies and Organizational Performance

This study evaluates the impact of Modern Management Competitive Intelligence Strategies (MCCI Strategies) on the performance of selected telecommunication firms. The construct of MMCI Strategies, which includes both tec...

Download PDF file
  • EP ID EP717210
  • DOI 10.47191/ijmra/v6-i6-14
  • Views 73
  • Downloads 0

How To Cite

Koffka Khan (2023). A Framework for Multi-Task Learning in Dynamic Adaptive Streaming Over HTTP. International Journal of Multidisciplinary Research and Analysis, 6(06), -. https://europub.co.uk/articles/-A-717210