Description: Applications are invited for an exciting 3-year PhD studentship to research on developing deep learning methods for action detection in videos. Action detection means action recognition plus localization of the actors in spatial and temporal dimensions. Localizing becomes a key component in the complex real-life scenario involving multiple people in actions. Action detection is typically solved by recognition on candidate regions within the frame in contrast to recognition on the whole region of the frame. The success of detection methods depends on striking a balance between precision and recall of informative regions localizing the actors. We will explore the usage of deep CNNs for activity detection in a multi-camera setting.
University of Sussex is a research intensive university and is in top 20 in the UK (The Guardian University league tables 2016 and The Times and Sunday Times Good University Guide 2016), in the sunniest part of UK, less than an hour by train to London, and less than half an hour by cycle to the Brighton Beach.
Application Instructions: Applications are invited from individuals with a 1st class or high upper 2nd class Bachelor's or Master's degree with distinction or merit in Computer Science, Statistics, Mathematics or Physics, and an interest in statistical machine learning, computer vision, and image analysis. Strong programming skills in at least one of C/C++/Matlab/Python are essential.
Funding amount: £14,057 tax free stipend plus a UK/EU fees waiver.
Deadline: January 4th, 2016.