Machine Learning Strategies for Visual Events Recognition

Call for Papers

The recent advances in the fields of machine learning and computer vision have made possible the automatic detection and recognition of actions, events, behaviors, and workflows from visual data. This research has initially started from applying simple (the so-called “shallow”) machine learning structures, like hidden Markov models, single-layer neural networks, support vector machines, Bayesian models, and Gaussian structures, on data of constrained visual conditions (rather simple and static background, single or few persons present, almost constant illumination conditions, etc.). But today, it has been extended to the use of “deep learning” schemes, like convolutional neural networks or deep belief networks on recognizing events within a complex and unconstrained environment, like outdoor conditions, crowded situations, and dynamic and clutter background scenes.

The goal of this special issue is to seek for innovative contribution in the above fields bringing together researchers from machine learning, image processing, and computer vision. The new research achievements should be demonstrated on real-world and complex application scenarios promoting the current research achievements. Potential topics include, but are not limited to:

• Deep learning with application in image analysis, multimedia, and vision
• Transfer learning methodologies with multimedia analysis applications
• Predicted and online learning techniques in processing multimedia data
• Object/human detection and tracking using advanced machine learning tools
• Fusion of multiple sensors in events/activity recognition
• Concept-based video browsing, indexing, and retrieval based on advanced learning strategies social-based video analysis
• Artificial intelligence tools for event-based relevance feedback
• Research projects in the respective fields (international standardization activities and national/international research projects)
• Real-life applications including, but not limited to, multisensorial environmental monitoring and crisis management, evacuation strategies, security and safety in large-scale environments, medical applications like fall detection, monitoring of patients' activities, and quality control on patients' acting exercises

Before submission authors should carefully read over the journal's Author Guidelines, which are located at http://www.hindawi.com/journals/am/guidelines/. Prospective authors should submit an electronic copy of their complete manuscript through the journal Manuscript Tracking System at http://mts.hindawi.com/ according to the following timetable:

Lead Guest Editor

• Anastasios Doulamis, Technical University of Crete, Chania, Crete, Greece

Guest Editors

• Alberto del Bimbo, University of Florence, Florence, Italy
• Jenny Benois-Pineau, University of Bordeaux, Talence, Bordeaux, France
• Nikolaos Doulamis, National Technical University of Athens, Athens, Greece
• Theodora Varvarigou, National Technical University of Athens, Athens, Greece