Skip to main content
Overview
Affiliations
AffiliationRoom numberTelephone
Assistant Professor in the Department of Computer ScienceMCS 2026+44 (0) 191 33 44854

Biography

I am an Assistant Professor in Computer Science at Durham University and a member of the Scientific Computing and VIVID groups. My research is in theoretical areas of Deep Learning, specifically looking at Deep Generative Models such as EBMs or with variational Baysian methods. Previously, I co-founded Durham University startup Intogral Limited (now Gliff.ai). Please visit my Website for more information about my research or visit my Google Scholar for a full ist of publications.

Research Highlights

Research within my group has led to the invention of Unleashing Transformers (ECCV 2022), which generate diverse high-resolution samples. We also invented Gradient Origin Networks (ICLR 2021), which show that you don't need to use encoders in autoencoders (here is a video by Yannic Kilcher on GONs). We've published Deep Generative Modelling: A Comparative Review (IEEE TPAMI 2021) with interest in non-adversarial models such a Denoising Diffusion Models for Anomaly Detection AnoDDPM (CVPR NTIRE 2022) and Unpaired Translation UNIT-DDPM. In other domains, we developed an extension of ray tracing for protein docking called Shape Tracing (IEEE BIBE 2020) and an end-to-end solution for Deep Learning Protein Conformational Space (PRX 2021). Our interdisciplinary research has also been applied in unsupervised Medical Anomaly Detection (IEEE ISBI 2021), Cross-Domain Imagery (ICPR 2021), Multi-view Transformers for Object Detection, and to generate 3D CT-like Images from 2D X-rays MedNeRF (IEEE EMBC 2022).

Teaching

I teach the L3 Deep Learning module (COMP3547), the Reinforcement Learning module and the year two Cyber Security submodule (COMP2211). Slides and other material are available in the Teaching section of my website. I also have a YouTube channel with a lot of Deep Learning and Reinforcement Learning Material.

Professional Activities

I am an Area Chair for BMVC and have been an AC in past BMVA meetings. I'm also the Admissions Tutor for Computer Science and in the past have been the Open Day coordinator. I've been an invited speaker at several conferences and universities, including the 2020 Cyber Operational Conference, and the Chinese University of Hong Kong (CUHK). I was a speaker on BBC Sunday Politics about Cyber Security spending in public bodies, and I am a regular reviewer for IEEE such as IEEE TPAMI, IEEE TIFS, IEEE TNNLS, IEEE TIP and IEEE TMI.

Publications

Conference Paper

Doctoral Thesis

  • Chris G. Willcocks (2013). Sparse Volumetric Deformation - Animating and rendering huge amounts of volumetric data using GPGPU computing. Durham University. PhD.

Journal Article

Supervision students