I’m a Principal Scientist at Adobe Research, based out of San Jose CA, where I lead the Cross-Modal Representation Learning (XRL) Group within the Imaging Lab.
I'm a part-time Professor in Computer Vision at Surrey's Centre for Vision Speech and Signal Processing (CVSSP), the UK's largest academic research group for Multi-modal Signal Processing. (Bio), where I founded and co-direct DECaDE, the Centre for the Decentralized Digital Economy, an EPSRC research centre which explores the intersection of AI and Distributed Ledger Technologies (DLT) and their potential to transform the creator economy.
My research fuses Computer Vision, Graphics and Machine Learning to tackle representative learning problems in visual media, with particular emphasis on content authenticity (e.g. tech to fight fakes and misinformation) and creative visual search (focusing on cross-modal e.g. style, search).
I'm the Course Director for MSc in Computer Vision, Robotics and Machine Learning and teach on Image Processing and Deep Learning (EEEM063). I'm a member of the EPSRC ICT Strategic Advisory Team (SAT) and APPG on Blockchain.
Recent Updates
-
EPSRC studentships available We have 2x PhD studentships awarded and now hiring in our group, joint with Adobe.
-
2x papers accepted to AAAI-23 Conf. on Artificial Intelligence.
-
Congratulations to Kar Balan on his successful PhD confirmation!
-
Upcoming Keynote at CVPR Workshop on Copy Detection (CVPR 2023) on AI/DLT for Content Provenance and Authenticity.
-
Keynote at 6th ECCV Workshop on Vision for Art (ECCV 2022) on Content Provenance and Authenticity.
-
4x ECCV 2022 papers accepted (and 1 workshop paper at ECCVW VISART) congrats to Dan, Andy, Tu, and Gemma.
-
Congratulations to Gemma Canet Tarres on her successful PhD confirmation
-
Keynote on robust content fingerprinting to fight misinformation presented at JPEG AHG on Fake Media and NFT.
-
Best Paper Prize awarded to Alex Black at CVMP 2021, for work on video fingerprinting to fight fake news.