Koffka Khan

Department of Computing and Information Technology, the University of the West Indies, St Augustine, Trinidad and Tobago, W.I.

Generative Adversarial Networks (GANs) have emerged as a powerful tool in the field of Dynamic Adaptive Streaming over HTTP (DASH) to enhance various aspects of video streaming. This paper presents a taxonomy that categorizes the applications and techniques of GANs in the context of DASH. The taxonomy covers several key dimensions, including video generation, compression, quality enhancement, bandwidth adaptation, dynamic bitrate streaming, and cross-modal applications. Within each dimension, specific subcategories are identified to capture the diverse applications of GANs in DASH. Additionally, evaluation metrics for assessing the quality and effectiveness of GAN-based approaches are discussed. The taxonomy serves as a comprehensive framework to understand and organize the different ways in which GANs can be utilized to improve the streaming experience in DASH. By providing an organized structure, this taxonomy facilitates better understanding, comparison, and exploration of GAN-based approaches in DASH and enables researchers and practitioners to identify areas for further research and development.

Generative Adversarial Networks, streaming, DASH, video, quality, adaption, bandwidth

1) Agnese, J., Herrera, J., Tao, H., & Zhu, X. (2020). A survey and taxonomy of adversarial neural networks for text‐to‐image synthesis. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(4), e1345.

2) Bisht, A., Mendes, A. C. D. S., Thoreson II, J. D., & Samavi, S. (2023). Low Latency Video Denoising for Online Conferencing Using CNN Architectures. arXiv preprint arXiv:2302.08638.

3) Chiariotti, F. (2021). A survey on 360-degree video: Coding, quality of experience and streaming. Computer Communications, 177, 133-155.

4) Dash, A., Ye, J., & Wang, G. (2021). A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines--From Medical to Remote Sensing. arXiv preprint arXiv:2110.01442.

5) Guo, Q., Feng, W., Gao, R., Liu, Y., & Wang, S. (2021). Exploring the effects of blur and deblurring to visual object tracking. IEEE Transactions on Image Processing, 30, 1812-1824.

6) He, Y., Seng, K. P., & Ang, L. M. (2023). Multimodal Sensor-Input Architecture with Deep Learning for Audio-Visual Speech Recognition in Wild. Sensors, 23(4), 1834.

7) Izima, O., de Fréin, R., & Malik, A. (2021). A Survey of Machine Learning Techniques for Video Quality Prediction from Quality of Delivery Metrics. Electronics, 10(22), 2851.

8) Khan, K., & Goodridge, W. (2018). Bandwidth Estimation Techniques for Relative 'Fair' Sharing in DASH. International Journal of Advanced Networking and Applications, 9(6), 3607-3615.

9) Khan, K., & Goodridge, W. (2018). Future DASH applications: A survey. International Journal of Advanced Networking and Applications, 10(2), 3758-3764.

10) Khan, K., & Goodridge, W. (2018). QoE in DASH. International Journal of Advanced Networking and Applications, 9(4), 3515- 3522.

11) Khan, K., & Goodridge, W. Markov Decision Processes for bitrate harmony in adaptive video streaming. In 2017 Future Technologies Conference (FTC), Vancouver, Canada, unpublished.

12) Koffka, K., & Wayne, G. (2018). A DASH Survey: the ON-OFF Traffic Problem and Contemporary Solutions. Computer Sciences and Telecommunications, (1), 3-20.

13) Lee, R., Venieris, S. I., & Lane, N. D. (2021). Deep neural network–based enhancement for image and video streaming systems: A survey and future directions. ACM Computing Surveys (CSUR), 54(8), 1-30.

14) Lee, Y., & Lee, S. (2020). Automatic colorization of anime style illustrations using a two-stage generator. Applied Sciences, 10(23), 8699.

15) Li, T., Huang, J., Risinger, E., & Ganesan, D. (2021, June). Low-latency speculative inference on distributed multi-modal data streams. In Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services (pp. 67- 80).

16) Li, W., Huang, J., Wang, S., Wu, C., Liu, S., & Wang, J. (2022). An apprenticeship learning approach for adaptive video streaming based on chunk quality and user preference. IEEE Transactions on Multimedia.

17) Li, W., Oteafy, S. M., Fayed, M., & Hassanein, H. S. (2020). Quality of experience in ICN: Keep your low-bitrate close and high- bitrate closer. IEEE/ACM Transactions on Networking, 29(2), 557-570.

18) Mentzer, F., Toderici, G. D., Tschannen, M., & Agustsson, E. (2020). High-fidelity generative image compression. Advances in Neural Information Processing Systems, 33, 11913-11924.

19) Saxena, D., & Cao, J. (2021). Generative adversarial networks (GANs) challenges, solutions, and future directions. ACM Computing Surveys (CSUR), 54(3), 1-42.

20) Shangguan, W., Sun, Y., Gan, W., & Kamilov, U. S. (2022, October). Learning cross-video neural representations for highquality frame interpolation. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XV (pp. 511-528). Cham: Springer Nature Switzerland.

21) Stockhammer, T. (2011, February). Dynamic adaptive streaming over HTTP-- standards and design principles. In Proceedings of the second annual ACM conference on Multimedia systems (pp. 133-144).

22) Wang, Y., Chan, P. H., & Donzella, V. (2023). Semantic-Aware Video Compression for Automotive Cameras. IEEE Transactions on Intelligent Vehicles.

23) You, A., Kim, J. K., Ryu, I. H., & Yoo, T. K. (2022). Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey. Eye and Vision, 9(1), 1-19.

24) Zhang, A., Wang, C., Han, B., & Qian, F. (2021, February). Efficient volumetric video streaming through super resolution. In Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications (pp. 106-111).

VOLUME 06 ISSUE 06 JUNE 2023

There is an Open Access article, distributed under the term of the Creative Commons Attribution – Non Commercial 4.0 International (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/), which permits remixing, adapting and building upon the work for non-commercial use, provided the original work is properly cited.