ElderMTL: Multi-Task Affect Monitoring for Elderly Care
Maria Razzhivina, Shahane Tigranyan, Aram Avetisyan, Ilya Makarov, Andrey Savchenko
Abstract
We present ElderMTL, a multi-task affect monitoring system designed for elderly care settings. The system simultaneously estimates Facial Action Units (FAUs), Valence-Arousal (VA) signals, and categorical emotions (FER) from video, capturing multiple layers of affective information. To improve sensitivity to subtle affective cues common in older adults, our approach incorporates age-conditioned physiological modeling, including baseline muscle adjustments and a dynamic AU co-activation graph. This enables the system to adapt to age-related changes in facial expression patterns, providing more reliable and interpretable emotion assessments. In a live demonstration, we showcase ElderMTL processing video streams, visualizing AU activations, affective state predictions, and interpretable insights that highlight age-specific affective dynamics. This work demonstrates that physiologically grounded, multi-task affective monitoring can provide meaningful, real-world support for elderly care.
BibTeX
@inproceedings{ijcai2026_eldermtlmultitas,
title = {ElderMTL: Multi-Task Affect Monitoring for Elderly Care},
author = {Maria Razzhivina and Shahane Tigranyan and Aram Avetisyan and Ilya Makarov and Andrey Savchenko},
booktitle = {IJCAI 2026},
year = {2026}
}