Research Officer on Summarizing Videos into Trailers
Research Officer on Summarizing Videos into Trailers
Faculty/Services: Faculty of Science
Educational level: Master
Function type: Support Staff
Closing date: 19 December 2021
Vacancy number: 7799
Do you want to investigate how computer vision and deep learning can help with making trailers for movies and series? In the media industry, trailers for video content such as movies and series form a core medium for building awareness, branding, and teasing the audience into watching. Producing trailers for movies and series is an expensive and labor-intensive task. Video content needs to be viewed in full, after which the most interesting scenes are manually selected and finally edited into a short trailer. A trailer for a 90-minute movie typically runs for only 10 to 30 seconds when broadcasted, but takes half a day to create. A core limitation in this setup is that editors need to spend most of their time dissecting video data manually. A second limitation that follows is that only a one-size-fits-all trailer without personalization can be produced for each video.
What are you going to do
In this one-year project you will research how to learn which scenes in movies and videos are most suitable for trailers. Starting from existing work in video summarization, we will build a network that learns the trailer-ness of scenes given visual and audial data. We will then integrate this network into a human-in-the-loop system, where editing experts use the trailer-ness to rank scenes and give feedback to the system about their current performance for continual learning. This project is jointly supervised by dr. Pascal Mettes (University of Amsterdam) and dr. Daan Odijk (RTL Nederland).
You are expected to:
implement and evaluate computer vision models;
actively collaborate with researchers from academia and industry;
where possible, publish papers together with the supervisors.
What do we require of you
A MSc degree in Artificial Intelligence, Computer Science, or a closely related field;
experience in working with computer vision models;
a collaborative mindset;
fluency in English and/or Dutch, both written and spoken.
We offer an employment contract for one year, preferably starting on 1 February 2022. The employment contract is for 38 hours a week.
Your salary, depending on your relevant experience on commencement of the employment contract, ranges between €2,700 to €3,606 gross per month. This sum does not include the 8% holiday allowance and the 8.3% year-end allowance. The Collective Labour Agreement for Dutch Universities (CAO NU) is applicable. Are you curious about our extensive package of secondary employment benefits like our excellent opportunities for study and development? Take a look here.
To work at the University of Amsterdam is to work in a discerning, independent, creative, innovative and international climate characterized by an open atmosphere and a genuine engagement with the city of Amsterdam and society. Here you can read more about working at the University of Amsterdam.
The University of Amsterdam is the largest university in the Netherlands, with the broadest spectrum of degree programmes. It is an intellectual hub with 39,000 students, 6,000 employees and 3,000 doctoral students who are all committed to a culture of inquiring minds.
Faculty of Science has a student body of around 7,000, 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
Want to know more about our organisation? Read more about working at the University of Amsterdam.
This project is a joint collaboration between the University of Amsterdam and RTL. You will be working with dr. Pascal Mettes at UvA and dr. Daan Odijk at RTL. Next to supervision, RTL also provides relevant in-house expertise on trailer production. Lastly, UvA and RTL will collaborate during the upcoming ICT with Industry project on automatic trailer production, allowing for a catalyst of this project.
Do you have any questions or do you require additional information? Please contact:
Pascal Mettes, Assistant Professor
Do you recognize yourself in the job profile? Then we look forward to receiving your application by 19 December 2021. You may apply online by using the link below.
Applications in .pdf should include:
a link to your Master’s thesis and grade transcripts.
Please mention the months (not just years) in your CV when referring to your education and work experience.
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.