Class-agnostic visual object tracking at Københavns Universitet

One example may be Class-agnostic object tracking. It is a challenging problem specially in cluttered environment because it is very difficult to learn a target specific discriminative model a priori. In the real life case, human visual cortex can do this task (where and what is the object) effectively by dynamically overwhelm inappropriate visual features. But computer, how? We can develop a Machine/deep learning model to solve this type of problem.

Supervisor: Sandeep Singh Sengar, sengar@di.ku.dk

About the Section of Machine Learning

The activities in the section range from research into the theoretical foundations of machine learning to applications within a broad set of domains, including remote sensing, information retrieval, medical image analysis and modelling of biological data.

The research section is divided into four areas:

  •        Machine Learning Theory
  •        Medical Imaging
  •        Information Retrieval
  •        Machine Learning in Biology

Read more here: https://di.ku.dk/english/research/machine-learning/

 

 

 

 

Remember to mention that you found this position on UCPH Projects & Jobs