PhD position in Deep Future Spatiotemporal Forecasting

Updated: 8 months ago
Deadline: 07 Feb 2020

Applications are invited for a PhD candidate to work on the research of Deep Future Spatiotemporal Forecasting. The successful candidate will be supervised by Dr Efstratios Gavves, based in the ISIS Lab at the University of Amsterdam led by Prof. Cees G.M. Snoek. The University of Amsterdam is a leading University consistently ranked in the top 50 worldwide, with a world-leading Computer Science research department. The position is together with the Autonomous Driving Department of BMW Group, a leading automotive manufacturer. The successful candidate is expected to regularly visit and work at the BMW Headquarters in Munich, Germany.

Project description

The research topic is ’Deep Future Spatiotemporal Forecasting’, the focus is on Machine Learning, Computer Vision and Deep Learning, for modelling temporal sequences such that to extrapolate to future prediction. This contrasts to today’s Deep Learning and Computer Vision largely focusing on explaining present observations (classification/segmentation/detection on the current frame). Forecasting the future is challenging as it concerns streaming and noisy and high-dimensional sequences, characterized by non-stationary statistics and high redundancy.

A typical example -and primary application for this project- is anticipating the future scenes, object locations and object trajectories from videos recorded from an (eventually autonomous) vehicle. Current vehicles already enjoy conditional automation (level 3 out of 5). The ultimate goal is fully autonomy (level 5 out of 5), a disproportionately hard objective. Future spatiotemporal forecasting is critical for reaching level 5 autonomy, avoiding accidents and minimizing discomfort to passengers. The forecasting will rely on various modalities including videos or 3d environmental models, recorded by on-car sensors like cameras, LIDARs, radars and other fused sensors. The student will study radical and novel learning and vision theories and frameworks to address the challenges in deep future spatiotemporal forecasting, including non-stationarity, feature slowness, good generalization or even causality. Research will be published in the top venues in computer vision and machine learning conferences and journals (CVPR, NeurIPS, ICCV, ICML, ECCV, ICLR).

The position is jointly held between the University of Amsterdam and the Autonomous Driving department of BMW Group. The student will conduct academic research at the University of Amsterdam, while consolidating research and evaluating methods on real data collected by experimental BMW autonomous vehicles. Successful trials will be further tested on experimental BMW autonomous vehicles. The research will be supervised by Dr. Efstratios Gavves based in the ISIS Lab at the University of Amsterdam, a world-leading vision and learning lab, situated next to renowned other AI labs like AMLab and ILPS with top AI researchers. The University of Amsterdam is a top-50 University with a world-leading Computer Science research department. The student will be co-supervised by Naveen Shankar Nagaraja, Machine Learning R&D Engineer at BMW Group, and expected to regularly visit and work at the BMW Headquarters in Munich, Germany.
For more information on the project visit:

What are you going to do?

As part of this position you are going to:

  • perform novel academic research on the crossroads of computer vision, machine learning and deep learning. Research will be published in the top conferences and journals, including CVPR, ICLR, ICCV, NeurIPS, ECCV, ICML, PAMI, IJCV, and so on;
  • visit at regular intervals the BMW Headquarters to work on, test and evaluate the research algorithms in simulators and real BMW test vehicles;
  • assist with teaching in the MSc courses of the University of Amsterdam, as per the standard contracts;
  • supervise MSc and BSc students with their projects and theses.

What do we require?
  • An MSc degree (or equivalent) in either Artificial Intelligence, Electrical/Computer Engineering, Computer Science, Physics, Mathematics or related fields;
  • a solid understanding of Machine Learning and Deep Learning. Publications to top conferences or journals (CVPR, NeurIPS, ICCV, ICML, ECCV, ICLR) are greatly appreciated;
  • excellent mathematical foundations. Special emphasis in statistics and probability theory, calculus and linear algebra;
  • excellent programming skills. Preferably Python, or other similar languages. Knowledge of a Deep Learning framework such as PyTorch or TensorFlow;
  • creativity and high motivation are greatly appreciated! A scientific track record is a strong advantage;
  • fluent communication and writing skills, cooperative spirit, excellent command of English.

Our offer

A temporary contract for 38 hours per week, preferably starting on 1 March 2020, for the duration of 4 years. The start date is flexible (initial appointment will be for a period of 18 months and after a satisfactory evaluation the contract will be extended for 30 months) and should lead to a dissertation (PhD thesis). We will draft an educational plan that includes attendance of courses and (international) meetings. We also expect you to assist in teaching undergraduates and master students.

The salary, depending on relevant experience before the beginning of the employment contract, will be €2,325 to €2,972 (scale P) gross per month, based on fulltime (38 hours a week), excluding 8% holiday allowance and an 8.3% end-of-year bonus. A favorable tax agreement, the '30% rule', may apply to non-Dutch applicants. The Collective Labour Agreement of Dutch Universities is applicable.

Are you curious about our extensive package of secondary employment benefits? Then find out more about working at the Faculty of Science .


Do you have questions about this vacancy? Or do you want to know more about our organisation? Please contact:

About the Faculty of Science

The Faculty of Science has a student body of around 6,500, as well as 1,600 members of staff working in education, research or support services. Researchers and students at the Faculty of Science are fascinated by every aspect of how the world works, be it elementary particles, the birth of the universe or the functioning of the brain.

The mission of the Informatics Institute is to perform curiosity-driven and use-inspired fundamental research in Computer Science. The main research themes are Artificial Intelligence, Computational Science and Systems and Network Engineering. Our research involves complex information systems at large, with a focus on collaborative, data driven, computational and intelligent systems, all with a strong interactive component.

Other than the ISIS hosting lab, world-class research groups directly involved in deep learning are AMLAB (machine learning led by prof. M. Welling) and ILPS (information retrieval led by prof. M. de Rijke). Examples of industry funded research labs involved in deep learning are Qualcomm-UVA (QUVA) Lab (12 PhDs/Postdocs), Bosch-UvA DELTA Lab (10 PhDs/Postdocs), Philips Lab (4 PhD/Postdocs) and SAP-UvA Lab (3 PhDs/Postdocs). We also have ongoing collaborations with Microsoft Research (2 PhD).

Since September 2010, the whole faculty has been housed in a brand new building at the Science Park in Amsterdam. Science Park is one of the largest centers of academic research in the Netherlands.

Job application

The UvA is an equal-opportunity employer. We prioritise diversity and are committed to creating an inclusive environment for everyone. We value a spirit of enquiry and perseverance, provide the space to keep asking questions, and promote a culture of curiosity and creativity.

The Informatics Institute strives for a better gender balance in its staff. We therefore strongly encourage women to apply for this position.

Do you recognize yourself in the job profile? Then we look forward to receiving your CV and cover letter by 7 February 2020. You may apply online by using the link below.

Applications should include:

  • a motivation letter explaining why you are the right candidate (max 1 page);
  • a research statement on how to approach Deep Future Spatiotemporal Forecasting (max 2 pages). Solid and creative ideas will be greatly appreciated!
  • a Curriculum Vitae (max 3 pages);
  • a copy of your MSc thesis. If your thesis is not in English, a translated summary or equivalent (max 4 pages);
  • a complete record of BSc and MSc courses, including grades. A list of projects you have worked on, describing briefly your contributions (max 2 pages). Your coursework and projects should motivate your competence in Machine Learning, Mathematics and Programming;
  • at least two academic references. Industrial references are also appreciated.


No agencies please

View or Apply

Similar Positions