Research Associate in Multimodal Video Understanding

The role

A strong and vibrant research team with steady-stream publications in high-calibre venues is looking for a postdoctoral researcher (26-months fixed-term) to develop novel approaches to multi-modal video understanding. The position is funded by two projects: EPSRC Program Grant Visual AI (PI: Andrew Zisserman) and EPSRC Fellowship grant Umpire (PI: Dima Damen). The applicant will thus be based in Bristol and collaborating with VGG in Oxford. The project will focus on integrating various input modalities (audio, video, depth) and output modalities (language, user feedback) to achieve better video understanding models

You will be working closely with Dima on her active research. Check Dima’s research interests and projects at: http://dimadamen.github.io/

Prior expertise in video analytics and deep learning methods with a strong publication track record is expected, including first-author publications in CVPR/ICCV/ECCV/BMVC/PAMI/IJCV/NeurIPS/ICLR.

What will you be doing?

Over the period of 26 months, you will be:

• Conducting novel research in multimodal video understanding – contributing novel research on designing, training (with minimal data or self-supervision) and evaluating video understanding models. This will include hands-on research using the latest deep learning approaches.
• Presenting your work in regular meetings, taking feedback and integrating the goals of the program grant into your individual research directions.
• Publishing in top-tier venues (conferences and journals). Communicating your work to the best possible audience.
• Collaborating with other researchers (postdocs and faculty) in the Visual AI project.
• Co-advising junior PGR students

You should apply if

• PhD in Video Understanding, preferably with expertise in video understanding or multimodal visual models.
• Prior degree in computer science, engineering or mathematics
• Detailed knowledge of video understanding state-of-the-art, approaches, datasets and problems, preferably with expertise in egocentric datasets and familiarity with EPIC-KITCHENS and/or Ego4D datasets.
• Experience in handling video data, for learning and inference
• Experience in modelling deep learning approaches for Video Understanding
• Experience and evidence of publishing at high-calibre conferences and journals (at least one first-author paper in a major venue – CVPR/ICCV/ECCV/BMVC/NeurIPs/PAMI/IJCV/Neurips/ICLR in the past 3 years).
• Excellent programming skills (Python)
• Proficiency in deep learning frameworks (PyTorch)

Additional information

For informal queries, please contact: Dima Damen: Dima.Damen@bristol.ac.uk 

To find out more about what it's like to work in the Faculty of Engineering, and how the Faculty supports people to achieve their potential, please see our staff blog:

https://engineeringincludesme.blogs.bristol.ac.uk/

We recently launched our strategy to 2030 tying together our mission, vision and values.

The University of Bristol aims to be a place where everyone feels able to be themselves and do their best in an inclusive working environment where all colleagues can thrive and reach their full potential. We want to attract, develop, and retain individuals with different experiences, backgrounds and perspectives – particularly people of colour, LGBT+ and disabled people - because diversity of people and ideas remains integral to our excellence as a global civic institution.

Advert information