Ph.D. - From Ontology to Visual Scene Understanding

The University of Manchester

Understanding visual scenes is one of the fundamental objectives of computer vision. A first step in scene understanding is the detection and recognition of objects from the input images, such as "person" or "bicycle", which is well-understood. A second step is the detection of visual relations between objects such as "person on bicycle" in the images, which is currently far more challenging. Machine learning models, such as neural networks, can in general be used to construct a mapping from an input image to a set of semantic relationships (or a scene graph) between the detected objects. However, success of state-of-the-art scene relation/graph extraction systems relies on the use of a very large amount of labeled image examples, called "ground truth".

This Ph.D. project will explore a different type of learning strategy, driven by information fusion and knowledge transfer. We plan to extend state-of-the-art example based learning to include: (1) processing and learning from existing knowledge in language domain and knowledge, and (2) integrating the learned knowledge with the image. We will analyse the trade-offs between purely ground-truth-based approaches and our extensions to include background knowledge, in particular for what kind of scenes what kind of knowledge can significantly reduce the need of ground truth.

This project lies in the fields of machine learning, computer vision, ontology and description logic.

We will consider applicants who have:
* Some existing knowledge in some of the above fields.
* Enthusiasm for research across the above research fields.
* An excellent undergraduate degree in Computer Science or Mathematics (or related discipline), and preferably, a relevant M.Sc. degree.
* Very good experience with computer programming of mathematical models and algorithms (in Python, Matlab or other platforms).
* Excellent report writing and presentation skills.
* Good ability to communicate with fellow students and colleagues.

Please, note that applicants must additionally satisfy the standard requirements for postgraduate studies at the University of Manchester, such as a first-class or high upper-second class (or an equivalent international qualification) and English language qualifications, as stated in the PGR guidelines.

Qualified applicants are strongly encouraged to informally contact the supervising academic Dr. Tingting Mu (tingting.mu@manchester.ac.uk) or Prof. Uli Sattler (Ulrike.Sattler@manchester.ac.uk) to discuss the application and possible research directions prior to applying.

Share this PhD
     
  Share by Email   Print this job   More sharing options
We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

PhD

Location(s):

Northern England