PhD Positions, Project 'Spatiotemporal Reconstruction of Interacting People for Perceiving Systems'

PhD Positions, Project 'Spatiotemporal Reconstruction of Interacting People for Perceiving Systems'

Published Deadline Location
1 Oct 31 Oct Amsterdam

Job description

The Computer Vision lab provides 3 fully-funded PhD positions as part of the ERC Starting Grant project STRIPES: SpatioTemporal Reconstruction of Interacting People for pErceiving Systems.

Do you want to help computers see, understand, and assist us, humans, in everyday life? Are you excited with 3D Machine Perception, 3D Human and Object Understanding, 3D Human Avatars, and Machine Learning? Do you want to conduct internationally-visible research in one of the world’s most exciting cities? We are searching for three strong PhD candidates to push together the state of the art!

Intelligent systems, such as robots or smart homes/offices, need to perceive humans in their natural habitat with affordable, energy-efficient and non-intrusive sensors, such as commodity color cameras. To this end, a long-standing goal of computer vision is to understand human actions from videos. Given a video, people effortlessly figure out what objects exist in it, the spatial layout of objects and the pose of humans. Moreover, they deeply understand the depicted action. What are people doing? Why are they doing this? What is their goal? How do they achieve this? To empower computers with the ability to infer and exploit such abstract concepts from pixels, we need to devise appropriate datasets and algorithms for perception, i.e. for estimating the shape and pose of people and objects, as well as their relative spatiotemporal relationship. This would revolutionize the use of intelligent systems for assistive applications ($31.22 billion market expected by 2030) and mixed reality ($6-13 trillion market expected by 2030); think of a virtual person registered as a hologram in our surroundings, helping us perform our household activities, or helping train professionals to use their equipment; think also of a robot that imitates people or collaborates with them for executing a task.

Since humans live in a 3D world, their actions involve interacting with 3D objects. Thus, to understand human actions, we need to reason in 3D, or in 4D with the time dimension, about humans and objects jointly. There is significant prior work on estimating 3D humans without taking into account objects and estimating 3D objects without taking into account humans. But, comparatively, there is little work on reconstructing 3D Human-Object Interactions (HOI) from images.

Despite the progress, the field is still at its infancy. Intelligent systems need methods that work on natural images/videos, so that the whole body is tracked reliably in 3D, the hand pose is captured, objects are also tracked, and body- and hand-object contact is realistic. However, essential components for this, such as interaction-aware representations for objects and humans, and estimating HOI from images/videos with contact and spacetime awareness, are still open problems. These are fundamental challenges and timely problems that call for a holistic approach.

We aim to tackle these by developing novel mathematical and computational HOI frameworks. To this end, we seek 3 PhD students to work on different, yet complementary, components of the project:
  • Position #1: Develop & evaluate novel generative models for 3D/4D HOI.
  • Position #2: Develop & evaluate novel methods for contact-aware 3D HOI reconstruction.
  • Position #3: Develop & evaluate novel methods for spacetime-aware 4D HOI reconstruction.

The positions are funded by a prestigious ERC Starting Grant. Moreover, they come with research freedom along some specified directions, i.e., projects can be refined according to the aligned interests of the advisor (PI) and PhD candidates, and how the community and the state of the art evolve.

The goal is performing cutting-edge fundamental research, publishing at top-tier venues, releasing data and code, and introducing new research problems. We highly value a strong computational and mathematical background along with strong creativity, curiosity, self-motivation and team spirit.

Let us know how your experience and interests fit with any of these positions!

What are you going to do?

Tasks and responsibilities:
  • Develop and evaluate new methods at the intersection of (3D) Computer Vision, Computer Graphics and Machine Learning, within the project context described above;
  • Collaborate with other people at the UvA, as well as (inter-)nationally;
  • Regularly present internally on your progress;
  • Regularly present intermediate research results at top-tier international conferences and workshops, and publish them in proceedings and journals;
  • Provide a reviewing service for top-tier conferences and journals;
  • Develop exciting demos for both the research community and for public outreach;
  • Assist in relevant teaching activities, e.g., lectures, labs, co-advising BSc/MSc students.
  • Complete and defend a PhD thesis within the official appointment duration of four years;

You will be advised by Dimitris Tzionas (DT, UvA). The main location will be the UvA (Amsterdam) and the brand-new Lab42 building. We work on the intersection of (3D) Computer Vision, Graphics and Machine Learning. We publish at top international venues (CVPR, ICCV, ECCV, SIGGRAPH/TOG, IJCV, TPAMI. We have expertise on statistical 3D models for human bodies/hands, 3D human shape/pose understanding, and (inter-)action understanding. We work on both 3D/4D perception from images and 3D/4D synthesis. Recently, DT received a prestigious ERC Starting Grant, while two papers co-authored by DT were best-paper finalists at CVPR 2022 and GCPR 2022. An immediate (growing) team of 2 PhDs (Dimitrije Antic, Georgios Paschalidis) working on related topics is available for tight interactions. A surrounding team (CV lab) of 7 senior researchers and 13 PhD students (and growing) is also available for interactions. Our strong international network (ELLIS society and beyond) can also lead to potential collaborations and/or internships.

Your profile

Your experience and profile:
  • You have a MSc degree (or equivalent) in Artificial Intelligence, Computer Science, Engineering, (Applied) Mathematics/Physics, or any other related field;
  • You have a strong background in (3D) Computer Vision, Graphics, and Machine Learning;
  • You have solid mathematics foundations (statistics, calculus, geometry and linear algebra);
  • You have excellent programming skills, especially in Python and PyTorch (C++ and CUDA are welcome);
  • You have strong communication, presentation and writing skills, and excellent command of English;
  • You are self-motivated, independent, creative, and you think critically and outside the box;
  • You are resistant to stress, when it gets busy you keep your cool;
  • You work successfully both independently and in a team.

Any of the following is a plus, but not necessary:
  • Hands-on experience with: AR/VR/MR, 3D geometry processing, 3D game/physics engines, SLAM, numerical optimization (e.g., ceres), deep learning (e.g., PyTorch), robotics (e.g., control, path planning), GPU programming (e.g., CUDA), natural language processing, foundational models;
  • Ideally you have a strong GitHub account;
  • Scientific publications, internships, industrial experience, contributions in open-source projects, participation in (inter-)national student competitions (e.g., robocup) – we would like to see if you have succeeded (or also failed) on something really challenging and the reasons behind this.

Our offer
A temporary contract for 38 hours per week for the duration of 4 years (the initial contract will be for a period of 18 months and after satisfactory evaluation it will be extended for a total duration of 4 years). The preferred starting date is January 2025 (or as soon as possible after this). This 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 gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 2,872 to € 3,670 (scale P), which is highly competitive internationally. This does not include 8% holiday allowance and 8,3% year-end allowance. The UFO profile ‘Promovendus’ (PhD Candidate) is applicable. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants. The Collective Labour Agreement of Universities of the Netherlands is applicable.

Besides the salary and a vibrant and challenging environment at Science Park we offer you multiple fringe benefits:
  • 232 holiday hours per year (based on fulltime) and extra holidays between Christmas and 1 January;
  • multiple courses to follow from our Teaching and Learning Centre;
  • a complete educational program for PhD students;
  • multiple courses on topics such as leadership for academic staff;
  • multiple courses on topics such as time management, handling stress and an online learning platform with 100+ different courses;
  • 7 weeks birth leave (partner leave) with 100% salary;
  • partly paid parental leave;
  • the possibility to set up a workplace at home;
  • a pension at ABP for which UvA pays two third part of the contribution;
  • the possibility to follow courses to learn Dutch;
  • help with housing for a studio or small apartment when you’re moving from abroad.

Are you curious to read more about our extensive package of secondary employment benefits, take a look here.

About us
The University of Amsterdam is the Netherlands' largest university, offering the widest range of academic programmes. At the UvA, 30,000 students, 6,000 staff members and 3,000 PhD candidates study and work in a diverse range of fields, connected by a culture of curiosity.

The Faculty of Science has a student body of around 8,000, as well as 1,800 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 (IvI) 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.

The ELLIS unit in Amsterdam is a local branch of the ELLIS Society, a diverse European network that promotes research excellence and advances breakthroughs in AI. With a focus on machine learning and machine intelligence within AI, the unit’s primary focus is promoting excellence at home and connecting local community members to relevant research and funding opportunities. This lays the foundation for the unit to facilitate high-quality international exchange, collaboration, and mutual development.

You will be working within the Computer Vision (CV) research group which focuses on studying core computer vision technologies and in particular colour processing, 3D reconstruction, object recognition, and human-behaviour analysis. The aim is to provide theories, representation models and computational methods which are essential for image and video understanding. Research ranges from image processing (filtering, feature extraction, reflection modeling, and photometry), invariants (color, descriptors, scene), image understanding (physics‐based, probabilistic), object recognition (classification and detection) to activity recognition with a focus on human‐behavior (eye tracking, facial expression, head pose, age and gender).

Want to know more about our organisation? Read more about working at the University of Amsterdam.

Any questions?
Do you have any questions or do you require additional information? Please contact:

Job application
If you feel the profile fits you, and you are interested in the job, we look forward to receiving your application. You can apply online via the button below. We accept applications until and including 31 October 2024.

Applications should include the following information (all files besides your cv should be submitted in one single pdf file):
  • a curriculum vitae; please note the months (not just the years) for your education and work experience; also include a possible starting date;
  • a motivation statement (0.5-1 page) that motivates your choice for this position; don’t list CV information, but include an explanation of what you aim to achieve professionally and scientifically through this project (Hints: Why do you need a PhD? Why do you want to do it with us? Why specifically this project? etc);
  • a research statement (max 2 pages) on how to approach the project. Solid and creative ideas will be greatly appreciated (for example: What are the main blockers/challenges? How would you imagine solving the problem? What are the advantages/disadvantages of this approach? How does this differ from the mainstream? Hint #1: think big and be bold. Hint #2: look into the literature and our publications, but also try to think beyond these);
  • a link to your Master’s thesis (you can also upload on your personal cloud) – if this is still work in progress, please write an extended abstract (max 1 page) and an estimated timeline for defending and graduating;
  • a link to your GitHub profile highlighting the most important repository – in case this repository is private, you can (anyhow) share a zip file with us on a confidential basis;
  • a complete record of Bachelor and Master courses, including grades and an explanation of the grading system;
  • a list of publications and/or 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 (please do not include any recommendation letters; we will contact them).

A knowledge-security check can be part of the selection procedure.
(for details: national knowledge security guidelines)

Only complete applications received within the response period via the link below will be considered.

The interviews will be held in the course of November. We will invite selected candidates for interviews on a rolling basis. Therefore, early applications are encouraged.

The UvA is an equal-opportunity employer. We prioritize 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.

If you encounter Error GBB451/ GBC451, please try using a VPN connection when outside of the European Union. Please reach out directly to our HR Department directly. They will gladly help you continue your application.

No agencies please.

Specifications

University of Amsterdam (UvA)

Specifications

  • PhD
  • Natural sciences
  • max. 38 hours per week
  • €2872—€3670 per month
  • University graduate
  • 13444

Employer

University of Amsterdam (UvA)

Learn more about this employer

Location

Science Park 904, 1098XH, Amsterdam

View on Google Maps

Interesting for you

X

Apply for this job

Apply for this job

This application process is managed by the employer (University of Amsterdam (UvA)). Please contact the employer for questions regarding your application.

Thank you for applying

Please contact the employer for questions regarding your application.

Tip: save this job as favorite in your AcademicTransfer account. This gives you an immediate overview and makes it easy to find the job later on. No account yet? Create it now and take advantage of other useful functionalities too!

Application procedure

Application procedure

Make sure to apply no later than 31 Oct 2024 23:59 (Europe/Amsterdam).