Scientific Rigour
There are very few people in the world with the knowledge necessary to design our AI solutions. It requires a PhD and a number of years of working in the field afterwards to even attempt to build an emotion recognition system that actually works, and it requires a team of people to detect medically relevant behaviour from face and voice analysis.
BlueSkeye AI has:
A dedicated data team of 14 people
10 people with relevant PhDs
A dedicated R&D team of 5 people with over with over 110 peer reviewed publications in relevant areas
Over 100 years of combined research experience in machine learning, face and voice analysis, and medicine
Our Co-founder and Chief Scientific Officer, Michel Valstar is the second most cited person in the world in social signal processing, an h-index of 51 and over 17k citations
Our Science
Below are a selection of just some of the important peer reviewed publications that have been integral to the development of our technology
Understanding human behaviour based on face and voice analysis
Spectral representation of behaviour primitives for depression analysis
S Song, S Jaiswal, L Shen, M Valstar
IEEE Transactions on Affective Computing
Automatic detection of ADHD and ASD from expressive behaviour in RGBD data
S Jaiswal, MF Valstar, A Gillott, D Daley
2017 12th IEEE International Conference on Automatic Face & Gesture …
Design and Evaluation of Virtual Human Mediated Tasks for Assessment of Depression and Anxiety
JO Egede, D Price, DB Krishnan, S Jaiswal, N Elliott, R Morriss, ...
Proceedings of the 21st ACM International Conference on Intelligent Virtual …
Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study
J Egede, MJG Trigo, A Hazzard, M Porcheron, E Bodiaj, JE Fischer, ...
Proceedings of the 21st ACM International Conference on Intelligent Virtual …
Self-supervised Learning of Person-specific Facial Dynamics for Automatic Personality Recognition
S Song, S Jaiswal, E Sanchez, G Tzimiropoulos, L Shen, M Valstar
IEEE Transactions on Affective Computing
E Sanchez, MK Tellamekala, M Valstar, G Tzimiropoulos
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …
How to distinguish posed from spontaneous smiles using geometric features
MF Valstar, H Gunes, M Pantic
Proceedings of the 9th international conference on Multimodal interfaces, 38-45
Personality Recognition by Modelling Person-specific Cognitive Processes using Graph Representation
Z Shao, S Song, S Jaiswal, L Shen, M Valstar, H Gunes
Proceedings of the 29th ACM International Conference on Multimedia, 357-366
Fundamental face analysis
Fully automatic recognition of the temporal phases of facial actions
MF Valstar, M Pantic
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 42 …
Action unit detection using sparse appearance descriptors in space-time video volumes
B Jiang, MF Valstar, M Pantic
2011 IEEE International Conference on Automatic Face & Gesture Recognition …
Audio-Visual Predictive Coding for Self-Supervised Visual Representation Learning
MK Tellamekala, M Valstar, M Pound, T Giesbrecht
2020 25th International Conference on Pattern Recognition (ICPR), 9912-9919
Deep learning the dynamic appearance and shape of facial action units
S Jaiswal, M Valstar
2016 IEEE winter conference on applications of computer vision (WACV), 1-8
Local evidence aggregation for regression-based facial point detection
B Martinez, MF Valstar, X Binefa, M Pantic
IEEE transactions on pattern analysis and machine intelligence 35 (5), 1149-1163
Cascaded continuous regression for real-time incremental face tracking
E Sánchez-Lozano, B Martinez, G Tzimiropoulos, M Valstar
European Conference on Computer Vision, 645-661
A transfer learning approach to heatmap regression for action unit intensity estimation
I Ntinou, E Sanchez, A Bulat, M Valstar, Y Tzimiropoulos
IEEE Transactions on Affective Computing
Social robotics and virtual assistants
Building autonomous sensitive artificial listeners
M Schroder, E Bevacqua, R Cowie, F Eyben, H Gunes, D Heylen, ...
IEEE transactions on affective computing 3 (2), 165-183
Databases, benchmarks, and tools
G McKeown, M Valstar, R Cowie, M Pantic, M Schroder
IEEE transactions on affective computing 3 (1), 5-17
The first facial expression recognition and analysis challenge
MF Valstar, B Jiang, M Mehu, M Pantic, K Scherer
2011 IEEE International Conference on Automatic Face & Gesture Recognition …
Avec 2013: the continuous audio/visual emotion and depression recognition challenge
M Valstar, B Schuller, K Smith, F Eyben, B Jiang, S Bilakhia, S Schnieder, ...
Proceedings of the 3rd ACM international workshop on Audio/visual emotion …
The NoXi database: multimodal recordings of mediated novice-expert interactions
A Cafaro, J Wagner, T Baur, S Dermouche, M Torres Torres, C Pelachaud, ...
Proceedings of the 19th ACM International Conference on Multimodal …
Web-based database for facial expression analysis
M Pantic, M Valstar, R Rademaker, L Maat
2005 IEEE international conference on multimedia and Expo, 5 pp.
For a complete set of relevant publications, please see Prof Valstar’s Google Scholar account.