The University of Amsterdam is inviting applications for PhD student on video understanding from few examples in the 2020/21 academic year.
While large amounts of cameras have been installed and even bigger amounts of video streams are being generated, the interpretation of these data is becoming an unsurmountable, error-prone and highly labor-intensive task. Automating the interpretation task through computers is the only way forward to survive this data deluge, but unfortunately it also is one of the hardest problems in artificial intelligence. To study this grand challenge, we will explore computer vision and deep learning, using tactics less demanding in terms of labeled examples. We will consider few-shot, cross-modal and active learning strategies able to recognize known activities of interest from limited amounts of human supervision. We also search for unknown and unforeseen activities by defining such anomaly recognition as a weakly-supervised spatiotemporal learning problem.
All research results will be evaluated in international competitions aiming for few-shot activity understanding and anomaly recognition, as well as in an integrated streaming video search engine for Amsterdam Schiphol Airport.
You are expected to:
- pursue, complete, and defend a PhD thesis within the appointed duration of four years;
- invent, evaluate and describe novel few-shot learning algorithms for spatiotemporal activity and anomaly recognition in video streams;
- contribute to a real-time video understanding showcase with their project partners;
- present research results at international conferences, workshops, and journals;
- become an active member of the research community and to collaborate with other researchers, both within and outside the Informatics Institute;
- assist in teaching activities, such as teaching labs and tutorials or supervising bachelor and master students.
Worth of Award
- The salary will be €2,325 to €2,972 (scale P) gross per month, based on full-time employment (38 hours a week).
- These amounts are exclusive 8% holiday allowance and 8,3% end-of-year bonus.
- A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants.
- have a Master’s degree in Computer Science, Artificial Intelligence, Computer Vision or a closely related field;
- have a strong background in one or more of computer vision, machine learning, and deep learning;
- are eager to tackle scientific problems in the area of video understanding;
- are able to implement and evaluate few-shot learning algorithms, e.g. using Python deep learning toolkits;
- are able to work well in teams and communicate fluently in written and spoken English.
How to Apply
Applications must include:
- a motivation letter explaining why you are the right candidate;
- curriculum vitae, (max 3 pages);
- a link to your Master’s thesis;
- a complete record of Bachelor and Master courses (including grades);
- a list of projects you have worked on (with brief descriptions of your contributions, max 2 pages);
- the names and contact addresses of at least two academic references.
All these should be grouped in one PDF attachment.
Deadline: Application closes July 1, 2020.