<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<div class=""><span style="font-size: 14px;" class="">We are looking for highly creative and motivated PhD students to work on visual scene understanding in <span style="orphans: 2; text-align: -webkit-auto; widows: 2;" class="">School of Computer Science, </span><span style="orphans: 2; text-align: -webkit-auto; widows: 2;" class="">The
University of Manchester, UK.</span></span></div>
<div class=""><span style="font-size: 14px; background-color: rgb(255, 255, 255);" class=""><br class="">
</span></div>
<div class=""><span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">Qualified applicants are strongly encouraged to informally contact the supervising academic Dr. Tingting Mu (</span><a href="mailto:tingting.mu@manchester.ac.uk" style="font-size: 14px;" class="">tingting.mu@manchester.ac.uk</a><span style="font-size: 14px;" class="">, </span><span style="font-size: 14px; orphans: 2; widows: 2;" class="">Homepage: </span><a href="http://personalpages.manchester.ac.uk/staff/tingting.mu/Site/About_Me.html" class="" style="font-size: 14px; orphans: 2; widows: 2;">http://personalpages.manchester.ac.uk/staff/tingting.mu</a><span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">)
or Prof. Uli Sattler (</span><a href="mailto:Ulrike.Sattler@manchester.ac.uk" style="font-size: 14px;" class="">Ulrike.Sattler@manchester.ac.uk</a><span style="font-size: 14px;" class="">, Homepage: </span><span style="background-color: rgb(255, 255, 255);" class=""><span style="font-size: 14px;" class=""><a href="http://www.cs.man.ac.uk/~sattler/" class="">http://www.cs.man.ac.uk/~sattler/</a></span></span><span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">)
to discuss the application and possible research directions prior to applying.</span></div>
<div class=""><br class="">
</div>
<div class=""><span style="background-color: rgb(255, 255, 255); font-size: 14px;" class="">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".</span></div>
<br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">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. </span><br style="margin: 0px; padding: 0px;" class="">
<br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">This project lies in the fields of machine learning, computer vision, ontology and description logic.</span><br style="margin: 0px; padding: 0px;" class="">
<br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">We will consider applicants who have: </span><br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">* Some existing knowledge in some of the above fields.</span><br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">* Enthusiasm for research across the above research fields. </span><br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">* An excellent undergraduate degree in Computer Science or Mathematics (or related discipline), and preferably, a relevant M.Sc. degree. </span><br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">* Very good experience with computer programming of mathematical models and algorithms (in Python, Matlab or other platforms). </span><br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">* Excellent report writing and presentation skills. </span><br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">* Good ability to communicate with fellow students and colleagues. </span><br style="margin: 0px; padding: 0px;" class="">
<br style="margin: 0px; padding: 0px;" class="">
<span style="font-size: 14px; background-color: rgb(255, 255, 255);" class="">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. </span><br style="margin: 0px; padding: 0px;" class="">
<br style="margin: 0px; padding: 0px;" class="">
<br class="">
</body>
</html>