Table of Contents Author Guidelines Submit a Manuscript

Geometric Analysis of Multimedia Data: Geometry as a Paradigm for Machine Learning and Data Mining in Multimedia Systems

Call for Papers

Nowadays, multimedia systems require processing, representation, storage, and transmission of large amount of multidimensional digital information, possibly sampled from nonlinear manifolds. On top of that, multimedia applications involve the computer-controlled integration of text, graphics, images/video, and audio represented in digital form with the goal of letting the user navigate, interact, create, and communicate insights inferred from sources of raw information. The complex tasks involved in such processes lead to a strong demand for multimedia data analysis and information extraction/retrieval.

In this context, manifold learning techniques have been applied to embed nonlinear data in lower dimensional spaces for subsequent analysis. The result allows a geometric interpretation of information with relevant consequences regarding data topology, sampling theory, similarity computation, pattern recognition, and, more recently, deep learning. Yet in the direction of using geometry as a paradigm for machine learning and data mining, we shall include the geometric data analysis and the development of tools for studying geometric features of data through topological data analysis.

The main goal of this special issue is to explore geometric concepts for analysis, data representation and integration, information extraction, and retrieval from multimedia systems. We encourage submissions that combine geometric concepts, data representation techniques, and machine and statistical learning methods, for extracting meaningful information from high-dimensional data spaces. Review articles that describe the current state of the art in geometric analysis of multimedia data are welcome as well.

Potential topics include but are not limited to the following:

  • Geometric analysis of deep hierarchical structures in multimedia
  • Generative models and manifolds for multimodal information retrieval
  • Data models integrating geometry, multivariate statistics, and sampling theory
  • Topological data analysis for studying geometric features of data
  • Multimedia data mining and analysis based on geometry and topology
  • Multimedia data analysis based on manifold learning
  • Geometric based approaches for metric learning
  • Geometry as a paradigm to discuss deep learning algorithms in multimedia applications

Authors can submit their manuscripts through the Manuscript Tracking System at

Submission DeadlineFriday, 7 September 2018
Publication DateJanuary 2019

Papers are published upon acceptance, regardless of the Special Issue publication date.

Lead Guest Editor

Guest Editors