ELLIS Postdoctoral Researcher VideoPredict - Causal video prediction

Description

We expect this project to advance the state of the art for the task of predicting future video content, and lead to testbeds for assessing whether a learned representation has correctly disentangled the independent causal mechanisms of a scene. Predicting future video content is a challenging task with high impact for a number of applications including self-driving cars and robotics, but also the generation of additional training data. Existing approaches range from predicting future actions with semantic labels to creating realistic renderings of future frames. Most of the current approaches are based on predictions given convolutional descriptors of previous frames. The goal here is to go beyond such representations and model the causality of the actions and disentangle motion and appearance. The approach envisioned will make the system more explainable and interpretable. It will hence result in more trustworthy AI for applications such as self-driving cars and robotics.

What we are looking for

Ideally, you bring along a strong research background in machine learning, statistics, artificial intelligence or a related field. You hold (or expect to shortly receive) a PhD in computer science, statistics, electrical engineering, mathematics or a related field and your research ability is demonstrated by publications in the leading machine learning / computer vision venues.

We are looking forward to meet someone with an active participation in scientific life and activity in the scientific community. The position also requires the ability to work independently in a highly collaborative and interdisciplinary environment.

The position offers a 2 years full time contract based on the German payscale of the collective wage agreement for the public service (TVöD Bund). It is based at the Max Planck Institute for Intelligent Systems in Tübingen, Germany. A 6 months (cumulative) exchange at our partner lab in France is required as a means to strengthen the cooperation and ensure the close scientific interaction on the project. This postdoc position will be part of the ELLIS P&P Program, for requirements, see https://ellis.eu/nomination-phd-postdoc. The project offers the opportunity to join forces between leading institutions in this field and to expand the frontiers of research.

We would like you to start this project as soon as possible. The position will be open until filled.

The Max- Planck Institute for Intelligent Systems

The MPI for Intelligent Systems and the University of Tübingen are leading institutions in the field of AI and machine learning. As part of the Cyber Valley Initiative, they have built an AI ecosystem that bridges the gap between academia and industry.

The successful applicant will be able to work with Bernhard Schölkopf (Director Empirical Inference Department MPI-IS Tübingen, Co-Director of the Tübinger AI Center, ELLIS Fellow) and Matthias Bethge (Professor for Computational Neuroscience und Machine Learning at the University of Tübingen, Director of the Tübinger AI Center, ELLIS Fellow).

INRIA Paris

INRIA is the French national research institute for digital science and technology. Its 200 project teams tackle ambitious research questions, often interdisciplinary and in collaboration with major research universities and industrial partners, with particular focus on bilateral collaborations with Germany.

VideoPredict is managed at the INRIA Paris Research Center by Cordelia Schmid (Research Director INRIA; ELLIS Unit France) and Jean Ponce (ELLIS Unit France, Scientific Director PRAIRIE 3IA Institute).

Paris and Tübingen have contributed significantly to the establishment of the European Lab for Learning and Intelligent Systems (ELLIS) and are committed to further inter-European synergies by connecting leading institutions within Europe. In this respect, the partnership between France and Germany is of vital importance.

How to apply

Please send your application (CV, motivational letter, transcripts, recommendation and publication list) as a single PDF to Mrs. Lidia Pavel, lpavel@tuebingen.mpg.de

If you wish to send a hard copy application, you may do so. Please address it to:

  Max Planck Institute for Intelligent Systems
  Prof. Dr. Bernhard Schölkopf
  Max-Planck-Ring 4
  72076 Tübingen
  Germany

The Max Planck society seeks to increase the number of women in those areas where they are underrepresented and therefore explicitly encourages women to apply. The Max Planck Society is committed to increasing the number of individuals with disabilities in its workforce and therefore encourages applications from such qualified individuals. The Max Planck society strives for gender diversity and equality.