I am a Senior Research Associate at the University of Bristol and a member of the MaVi research group. My current research focuses on Multimodal Learning, aiming to develop methods that integrate complementary sources of information to better understand dynamic real-world environments.
Previously, during my PhD in Computer Vision at the University of Bristol, supervised by Prof. Dima Damen, my research focused on leveraging multimodal data for egocentric video understanding. This included audio-visual learning, predicting upcoming object interactions using eye-gaze and 3D information, and long-term 3D dynamic object tracking. As part of this research, I spent a PhD internship with the Visual Representation Learning team at NAVER Labs Europe. Following my PhD, I continued as a Research Associate at the University of Bristol, contributing to work on 4D Video Understanding. My PhD thesis is available here.
Prior to my PhD, I earned a First Class Honours MEng in Computer Science from the University of Bristol, where my dissertation on "Video GANs for Human-Object Interactions" was highly graded. Alongside research, I have gained teaching experience across multiple undergraduate modules, contributing to both coursework design and lab-based support.
My technical strengths lie in deep learning, computer vision, and multimodal modelling, with extensive experience in Python (PyTorch), alongside experience with C++ and JavaScript.
jacob (dot) chalk (at) bristol (dot) ac (dot) uk
* denotes equal contribution
European Conference on Computer Vision (ECCV), 2026
arXiv preprint arXiv:2512.16456, 2025
Conference on Computer Vision and Pattern Recognition (CVPR), 2025
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023