Andrew Fitzgibbon

Registered user since Wed 2 Feb 2022

Name:Andrew Fitzgibbon
Bio:

Andrew Fitzgibbon has been closely involved in the delivery of three groundbreaking computer vision systems over two decades. In 2000, he was computer vision lead on the Emmy-award-winning 3D camera tracker “Boujou”; in 2009 he introduced large-scale synthetic training data to Kinect for Xbox 360, and in 2019 was science lead on the team that shipped fully articulated hand tracking on HoloLens 2. His passion is bringing the power of mathematics to the crucible of real-world engineering. He has numerous research awards, including ten “best paper” prizes at leading conferences, and is a Fellow of the UK’s Royal Academy of Engineering.

Country:United Kingdom
Affiliation:Graphcore
Personal website:http://www.fitzgibbon.ie
Research interests:Computer Vision, Machine Learning, Programming Languages

Contributions

PLDI 2022 Author of (POPL 2022) Provably Correct, Asymptotically Efficient, Higher-Order Reverse-Mode Automatic Differentiation within the SIGPLAN Track-track
POPL 2022 Author of Provably Correct, Asymptotically Efficient, Higher-Order Reverse-Mode Automatic Differentiation within the POPL-track
PLDI 2021 Author of Hashing Modulo Alpha-Equivalence within the PLDI-track
ICFP 2019 Author of Efficient Differentiable Programming in a Functional Array-Processing Language within the Research Papers-track
FHPC 2017 Author of Destination-Passing Style for Efficient Memory Management within the FHPC 2017-track