Federica Bruno
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Federica Bruno has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Ahmad Addoum
R&D Lab, ISART DIGITAL, Paris, France
1 shared publication - Fabio Solari
Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genoa, Genoa, Italy
1 shared publication - Guillaume Sacco
CHU Nice, Université Côte d'Azur, Nice, France
1 shared publication - Manuela Chessa
Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genoa, Genoa, Italy
1 shared publication - Razeen Hussain
Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genoa, Genoa, Italy
1 shared publication - Valeria Manera
CoBTeK Lab, Université Côte d'Azur, Nice, France
1 shared publication
Latest Publications
- Open Access
- 28 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 65-71
Are Digital Characters Suitable for Emotion Recognition Tasks? An Evaluation Study Using MetaHumans
Dementia is often accompanied by impairments in social cognition, such as reduced empathy and difficulties in emotion recognition, which negatively impact daily functioning and increase caregiver burden. Early detection of these deficits is crucial, yet traditional assessments relying on paper-and-pencil tests or actor-based stimuli face limitations in scalability and standardization. Advances in digital technologies, particularly high-fidelity digital characters such as MetaHumans, offer a more flexible and ecologically valid alternative. This pilot study compared MetaHuman digital characters with a validated set of human actor videos in an emotion recognition task involving 20 participants. Six basic emotions (Joy, Sadness, Anger, Fear, Surprise, and Disgust) were presented, and performance was evaluated through recognition accuracy, response times, perceived naturalness, and subjective ratings. MetaHumans achieved significantly higher accuracy and comparable response times, although actors were rated slightly more natural. These findings suggest that MetaHumans can provide standardized, reproducible, and cost-effective stimuli for assessing social cognition.
- 28 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 65-71
Open AccessAre Digital Characters Suitable for Emotion Recognition Tasks? An Evaluation Study Using MetaHumans
Dementia is often accompanied by impairments in social cognition, such as reduced empathy and difficulties in emotion recognition, which negatively impact daily functioning and increase caregiver burden. Early detection of these deficits is crucial, yet traditional assessments relying on paper-and-pencil tests or actor-based stimuli face limitations in scalability and standardization. Advances in digital technologies, particularly high-fidelity digital characters such as MetaHumans, offer a more flexible and ecologically valid alternative. This pilot study compared MetaHuman digital characters with a validated set of human actor videos in an emotion recognition task involving 20 participants. Six basic emotions (Joy, Sadness, Anger, Fear, Surprise, and Disgust) were presented, and performance was evaluated through recognition accuracy, response times, perceived naturalness, and subjective ratings. MetaHumans achieved significantly higher accuracy and comparable response times, although actors were rated slightly more natural. These findings suggest that MetaHumans can provide standardized, reproducible, and cost-effective stimuli for assessing social cognition.