Contact
Press and media
Many of our academics speak to the media as experts in their field of research. If you are a journalist, please contact the University’s Media and PR Team:
Biography
Jacob Chalk is a Research Associate at the University of Bristol and a member of the MaVi group. His research focuses on 4D video understanding, aiming to develop systems that can perceive and reason about dynamic 3D scenes over time, including problems such as long-term 3D object tracking. Previously, his work centred on leveraging multimodal data for egocentric video understanding, including audio-visual learning and prediction of object interactions using eye-gaze and 3D annotations.
Publications
Recent publications
13/08/2025HD-EPIC
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Spatial Cognition from Egocentric Video
2025 International Conference on 3D Vision (3DV)
EPIC-SOUNDS
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
TIM
Epic-Sounds
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Thesis
Leveraging Multimodal Data for Egocentric Video Understanding
Supervisors
Award date
20/01/2026
Teaching
For Software Product Engineering (Year 2) and Games Project (Year 3), Jacob supported group-based project work. He mentored assigned student teams and provided guidance on technical issues, software design decisions, development practices, and project organisation. His role involved responding to team queries during scheduled sessions and supporting progress towards the project goal(s).
For Computer Graphics (Year 3) and Image Processing and Computer Vision (Year 3), Jacob acted as a laboratory assistant. During lab sessions, he answered technical and coursework-related questions, clarified concepts introduced in lectures, and provided guidance on implementation and debugging tasks. His involvement was focused on supporting students during hands-on practical work.
In Applied Deep Learning (Year 4), Jacob provided laboratory assistance and supported students with model implementation, experimentation, and interpretation of results. He also contributed to the development of coursework and participated in marking and feedback.


