Skip to Main content Skip to Navigation
New interface
Conference papers

FLAME: Facial Landmark Heatmap Activated Multimodal Gaze Estimation

Neelabh Sinha 1 Michal Balazia 1 Francois F Bremond 1 
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : 3D gaze estimation is about predicting the line of sight of a person in 3D space. Person-independent models for the same lack precision due to anatomical differences of subjects, whereas person-specific calibrated techniques add strict constraints on scalability. To overcome these issues, we propose a novel technique, Facial Landmark Heatmap Activated Multimodal Gaze Estimation (FLAME), as a way of combining eye anatomical information using eye landmark heatmaps to obtain precise gaze estimation without any person-specific calibration. Our evaluation demonstrates a competitive performance of about 10% improvement on benchmark datasets ColumbiaGaze and EYEDIAP. We also conduct an ablation study to validate our method.
Complete list of metadata
Contributor : Neelabh Sinha Connect in order to contact the contributor
Submitted on : Wednesday, October 20, 2021 - 9:59:37 AM
Last modification on : Saturday, June 25, 2022 - 11:53:04 PM
Long-term archiving on: : Friday, January 21, 2022 - 7:08:10 PM


Files produced by the author(s)



Neelabh Sinha, Michal Balazia, Francois F Bremond. FLAME: Facial Landmark Heatmap Activated Multimodal Gaze Estimation. AVSS 2021 - 17th IEEE International Conference on Advanced Video and Signal-based Surveillance, Nov 2021, Virtual, United States. ⟨10.1109/AVSS52988.2021.9663816⟩. ⟨hal-03386581⟩



Record views


Files downloads