Keywords3D, Semantic Understanding, Machine Learning, Deep Neural Networks
This research will advance computer vision and machine learning methods enabling to create dynamic 3D models of complex scenes that can be fully understood by the machine, i.e. where the scene is represented as a graph of objects, attributes and their relationships. New sensor devices such as 3D or even holographic cameras will be considered. Applications will be selected in the areas of interaction (where current systems have been designed and are essentially usable in constrained situations, such as for gaming only), and media production: a specific target will be to generate audio descriptions of the scenes, which could have a very strong impact on future media production. The research will allow the candidate to develop a unique and transferable expertise in advanced machine learning, AI and Big Data. The researcher will be integrated within a significant group of deep learning researchers involved in regional and international collaboration with world-leading labs in the area.