CV
May 2021 - Present
Senior Research Scientist at Meta GenAI (formerly Facebook AI) - London UK.
Working on 3D and video generative AI.
Previously worked on helping advertisers to automatically generate Ads images with generative AI.
August 2019 - May 2021
Research Scientist at Samsung AI Center - Cambridge UK.
Working with Maja Pantić and Tony Xiang on deep learning for action recognition and affect recognition from static images and videos.
October 2018 - March 2019
Research Intern at Samsung AI Center - Cambridge UK.
Working with Maja Pantić on deep learning models applied to affect recognition from static images.
October 2015 - October 2018
Teaching assistant at Imperial College London.
Course Support Leader in graphics: coded the open source OpenGL framework used for the coursework
Personal tutor in mathematics for first year undergraduate students
Lab helper in C programming
Co-supervised MSc and BEng projects in computer graphics
Education
2014-2019
Imperial College London
PhD student in measurement-based realistic computer graphics supervised by Dr Abhijeet Ghosh. Centre for Doctoral Training in High Performance Embedded and Distributed Systems (HiPEDS). First year MRes awarded with Distinction.
2013-2014
Imperial College London
MSc in Advanced Computing awarded with Distinction.
2011-2014
Telecom ParisTech, formerly known as ENST – Paris, France
One of France's top engineering schools in the "Grandes Ecoles" system. Equivalent to a top-tier University specializing in engineering. Awarded the French Diplôme d’Ingénieur.
2008-2011
Preparatory Classes : Marcelin-Berthelot, Saint-Maur-Des-Fossés, France
Advanced Mathematics and Physics class. Preparation for the competitive entrance examinations to French Engineering Schools in the "Grandes Ecoles" system.
Publications
For a detailed list of my publications, please see the publications page.
Raphael Bensadoun∗, Tom Monnier∗, Yanir Kleiman∗, Filippos Kokkinos, Yawar Siddiqui, Mahendra Kariya, Omri Harosh, Roman Shapovalov, Benjamin Graham, Emilien Garreau, Animesh, Karnewar, Ang Cao, Idan Azuri, Iurii Makarov, Eric-Tuan Le, Antoine Toisoul, David Novotny†, Oran Gafni†, Natalia Neverova†, Andrea Vedaldi† - ∗Joint first authors, †Senior contributors
Arxiv 2024
Move Anything with Layered Scene Diffusion
Jiawei Ren, Mengmeng Xu, Jui-Chieh Wu, Ziwei Liu, Tao Xiang, Antoine ToisoulCVPR 2024, Seattle, USA.
Estimation of continuous valence and arousal levels from faces in naturalistic conditions
Antoine Toisoul, Jean Kossaifi, Adrian Bulat, Georgios Tzimiropoulos and Maja Pantic
Nature Machine Intelligence, 2021
Few-shot Action Recognition with Prototype-centered Attentive Learning
Xiatian Zhu, Antoine Toisoul, Juan-Manuel Pérez-Rúa, Brais Martinez, Li Zhang, Tao Xiang
BMVC 2021
Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention
Juan-Manuel Perez-Rua, Brais Martinez, Xiatian Zhu, Antoine Toisoul, Victor Escorcia, Tao Xiang
BMVC 2021
SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild
Jean Kossaifi, Robert Walecki, Yannis Panagakis, Jie Shen, Maximilian Schmitt, Fabien Ringeval, Jing Han, Vedhas Pandit, Antoine Toisoul, Bjorn Schuller, Kam Star, Elnar Hajiyev, and Maja Pantic
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.
Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation
Antoine Toisoul*, Jean Kossaifi*, Adrian Bulat, Yannis Panagakis, Timothy Hospedales, Maja Pantic (* Joint first authors).
CVPR 2020, Seattle, USA.
Egocentric Action Recognition by Video Attention and Temporal Context
Juan-Manuel Pérez-Rua, Antoine Toisoul, Brais Martinez, Victor Escorcia, Li Zhang, Xiatian Zhu, Tao Xiang.
Proceedings of the IEEE conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2020, Seattle, USA. (3rd position at the Epic-Kitchens Challenge of CVPR 2020)
Practical Measurement-based Modeling and Rendering of Surface Diffraction
Antoine Toisoul
PhD thesis, 2019
Acquiring Spatially Varying Appearance of Printed Holographic Surfaces.
Antoine Toisoul*, Daljit Singh Dhillon*, Abhijeet Ghosh (* Joint first authors).
ACM Transactions on Graphics (Proc. SIGGRAPH Asia), 37(6), 2018. Tokyo, Japan
Real-time rendering of realistic surface diffraction with low rank factorisation
Antoine Toisoul and Abhijeet Ghosh
Proc. of European Conference on Visual Media Production (CVMP), Dec. 2017. London, UK.
Practical Acquisition and Rendering of Diffraction Effects in Surface Reflectance
Antoine Toisoul and Abhijeet Ghosh
ACM Transactions on Graphics, 2017 (presentation at SIGGRAPH 2017). Los Angeles, USA.
Accessible GLSL Shader Programming
Antoine Toisoul, Daniel Rueckert, Bernhard Kainz
Proc. EuroGraphics 2017. Lyon, France.
Image-Based Relighting using Room Lighting Basis
Antoine Toisoul and Abhijeet Ghosh
Proc. of European Conference on Visual Media Production (CVMP), Dec. 2016. London, UK.
Awards
Second prize at the 2018 PhD Google Poster competition of Imperial College London
Second prize at the 2016 PhD Google Poster competition of Imperial College London
Best HiPEDS MRes 2015 individual project with 91%
Peer review
Reviewer for :
CVPR (2025, 2024, 2023, 2022)
SIGGRAPH (2021, 2020)
SIGGRAPH Asia 2020
ECCV 2022
ICCV 2021
Proceedings of the National Academy Of Sciences of the United States of America (PNAS)
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Image And Vision Computing journal.
MEDIA coverage
January, 29th, 2021 : Our Nature Machine Intelligence paper entitled “Estimation of continuous valence and arousal levels from faces in naturalistic conditions” has been featured in the Chinese media!
January, 26th, 2021 Our paper Estimation of continuous valence and arousal levels from faces in naturalistic conditions has been featured in TechXplore!
November, 14th, 2018 Our paper Acquiring Spatially Varying Appearance of Printed Holographic Surfaces has been featured in the Japanese media Seamless.
October, 31st, 2018 Our paper Acquiring Spatially Varying Appearance of Printed Holographic Surfaces has been featured in an episode of Two Minute Papers called Real-Time Holography Simulation!