Joint co-organization of a special session on “Recent advances in biometric technology for mobile devices” (RABTMD 2018) at the International conference on biometrics: theory, applications and systems (BTAS 2018) Organizers: Abhijit Das (STARS, Inria), Antitza Dantcheva (STARS, Inria), Hu Han (ICT-CAS), Jean-Luc Dugelay (Eurecom), Raghavendra Ramachandra (NTNU), Chiara Galdi (Eurecom)
New scientific publication: Das, Abhijit; Galdi, Chiara; Han, Hu; Ramachandra, Raghavendra; Dugelay, Jean-Luc; Dantcheva, Antitza”Recent advances in biometric technology for mobile devices”, in Proceedings of International conference on biometrics: theory, applications and systems (BTAS), 2018.
Gala dinner at ICPR’18:
Abhijit Das, Antitza Dantcheva, Francois Bremond won the ECCV’18 challenge on bias estimation in face analysis (BEFA). The challenge placed focus on a pertinent, but largely neglected issue – the biasness of face analytics datasets, with respect to factors such as age, gender, ethnicity, pose and resolution. In order to progress toward balanced face recognition and attribute estimation truly in the wild, the BEFA – challenge introduced a well-balanced dataset across multiple factors: age, gender, ethnicity, pose and resolution and requested for algorithms to estimate biases.
We proposed a Multi-Task Convolutional Neural Network (MTCNN) algorithm that jointly learned gender, age and ethnicity by a loss function involving joint dynamic loss weight adjustment and was successful, as well as relatively unbiased in estimating age, gender and ethnicity. More details here.
Joint co-organization of a special session on “Human Health Monitoring Based on Computer Vision” at the 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG2019) May 14-18, 2019, Lille, France. Organizers: François Brémond STARS, Inria), Xilin Chen (ICT, CAS), Hu Han (ICT, CAS), Abhijit Das (STARS, Inria), Antitza Dantcheva (STARS, Inria). More details can be found here (http://fg2019.org/participate/special-sessions/hhmbcv/).