Multimedia Tools and Applications - Call for Papers: AI and Machine Learning for Multimedia Applications [1253]
Aims, Scope, and Topics of Interest
The rise of machine learning approaches, in particular deep learning, has led to significant improvements in the performance of AI-based systems, and many current multimedia applications include at least one AI-based component. Images, video, sound, and text—traditional multimedia data—are now completed by a multitude of multimodal sources, on which the fundamental principles of multimedia research are being applied.
Multimedia is generated very rapidly, for example via social networks, human observation, and generative models. Hence, the training of machine learning models for multimedia data must be done incrementally for many applications, with incremental learning approaches becoming more and more popular in multimedia. Furthermore, in the case of distributed systems analysing multimedia data locally, e.g. for data privacy protection, the incremental adjustment of local models must be integrated into the global model. The latter has a better generalisation power as it is trained on a larger amount of data than each local model. The best way to integrate local model updates into the global model is the subject of federated learning. Finally, when applying multimedia fusion principles in different domains supplying multimodal data, such as remote sensing, astrophysics or mechanics, medical and healthcare multimedia applications, domain-dependent constraints/physical models of data may be integrated into model training yielding more reliable solutions.
The use of AI, however, has also raised the question of the reliability and explainability of their predictions for decision-making (e.g., the black-box issue of deep models). Such shortcomings undermine the trustworthiness of AI-based multimedia applications. It is therefore critical to understand how the predictions of AI-based systems correlate with information perception and expert decision-making. This is also an important prerequisite for successful teaming of human experts and AI-based tools. The objective of eXplainable AI (XAI) is in proposing methods to understand and explain how these systems produce their decisions.
The topics of interest of the Special Issue include:
● Incremental learning in multimedia
● Federated learning in multimedia
● Machine learning architectures for multimedia, in particular supporting multimodal data
● Physical models in AI with applications in multimedia
● Explainable/interpretable machine learning for multimedia
● XAI evaluation and benchmarks for multimedia data
● Information visualisation for models or their predictions
● Sample-centric and dataset-centric explanations in multimedia applications
Important Dates
Submissions Open: September 18, 2024
Submission Deadline: November 30, 2024
Guest Editors
Björn Þór Jónsson, Reykjavik University, Reykjavik, Iceland
Claudio Gennaro, ISTI-CNR, Pisa, Italy
Ewa Kijak, IRISA, Rennes, France
Stéphane Marchand-Maillet, University of Geneva, Geneva, Switzerland
Submission Guidelines
Authors should prepare their manuscript according to the Instructions for Authors available from the Multimedia Tools and Applications website (this opens in a new tab). Authors should submit through the online submission site at https://www.editorialmanager.com/mtap/default.aspx (this opens in a new tab) and select “SI 1253- AI and Machine Learning for Multimedia Applications” when they reach the “Article Type” step in the submission process. Submitted papers should present original, unpublished work, relevant to one of the topics of the special issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least three independent reviewers. It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process. Please note that the authors of selected papers presented at CBMI 2024 are invited to submit an extended version of their contributions by taking into consideration both the reviewers’ comments on their conference paper, and the feedback received during presentation at the conference. It is worth clarifying that the extended version is expected to contain a substantial scientific contribution, e.g., in the form of new algorithms, experiments or qualitative/quantitative comparisons, and that neither verbatim transfer of large parts of the conference paper nor reproduction of already published figures will be tolerated. The extended versions of CBMI 2024 papers will undergo the standard, rigorous journal review process and be accepted only if well-suited to the topic of this special issue and meeting the scientific level of the journal. Final decisions on all papers are made by the Editor in Chief.