Applied Artificial Intelligence and Machine Learning for Video Coding and Streaming Call for Papers

Call for Papers IEEE Open Journal of Signal Processing

Special Issue on

Applied Artificial Intelligence and Machine Learning for Video Coding
and Streaming

Please note that IEEE Open Journal of Signal Processing (OJSP) is a
Gold Open Access journal, however, open access fees for papers
accepted in this Special Issue will be waived; i.e. accepted papers
will be published free of charge.

Scope: Video traffic constituted 75% of all IP traffic in 2017 and
will constitute 82% of all IP traffic by 2022. Improving video co ding
methods and video networking schemes is therefore vital to cope with
this increasing demand. In recent years, we have witnessed how
Artificial Intelligence (AI) and Machine Learning (ML) revolutionized
the field of video coding and streaming as these new solutions now
offer state-of-the-art in many high-level and low-level image and
video related tasks. A range of Convolutional Neural Networks
(CNN)-based video coding tools (rate-distortion optimization,
deblocking filters, interpolation filters, chroma from luma prediction
methods), learned entropy coding, end-to-end image compression
techniques, decision trees based encoder speed ups, fuzzy network
bandwidth prediction, and video network resource allocation via
reinforcement learning are among these efforts. MPEG Ad Hoc Group on
deep neural networks based video coding and JPEG’s learning-based
image coding activity, are among recent initiatives which show that
significant effort is required to advance this field and overcome the
existing challenges such a s improving the compression efficiency,
lowering the overhead of computations of these AI/ML tools, finding
suitable loss functions and optimization criteria, managing network
resource according to user experience, accurately predicting network
status, and working towards explainable AI. As both academic and
industry efforts in this direction have been increasing tremendously,
this is the right time to focus on this topic.

For this Special Issue, we invite submissions of papers from the
academia and the industry reporting on the latest scientific and
engineering results and findings in applying AI and ML to video coding
and steaming. Topics of interest include, but are not limited to:

* Towards applicable end-to-end learned image/video compression
* Interpretability and explainability of learned models for video compression
* Low complexity, energy efficient, and memory efficient AI/ML for
image/video coding
* Distance metrics and optimization criteria for AI/ML-based
compression techniques
* Standard-compliant techniques to integrate AI/ML into video coding
and streaming
* Generative models for video compression and enhancement of compressed video
* Pre/post processing AI/ML techniques to enhance image/video coding
* AI/ML-based video saliency detection and coding
* AI/ML-based network resource prediction and content adaptation for
video streaming
* AI/ML-based solutions for co-optimization of network and video coding
* Smart network resource allocation for video streaming services
* AI/ML-based video traffic classification and prediction for video communication
* AI/ML-based video quality assessment, and QoE estimation for video streaming
* Real-time AI/ML-based video enhancement for efficient video coding
* ML-based packet video network fault detection, isolation, and diagnosis

* Initial Paper Submission: December 15, 2020
* Initial Paper Decision: January 30, 2021
* Revised Paper Submission: March 1, 2021
* Final Decision: March 15, 2021

Please follow IEEE OJSP's paper format and requirements. Once your
paper is ready, please submit it via IEEE OJSP's submission site, and be sure to select this
Special Issue when submitting. For more information, please contact
the lead Guest Editor Dr. Marta Mrak at .

Guest Editors:
* Marta Mrak, BBC R&D, UK
* Mahmoud Reza Hashemi, University of Tehran, Iran
* Shervin Shirmohammadi, University of Ottawa, Canada
* Ying Chen, Alibaba Cloud Intelligence Group, US
* Moncef Gabbouj, Tampere University, Finland