Research
Machine learning on human signals — face, eye, gait, voice.
Mental health sensing
Depression, mood and affect read from the phone you already carry.
[C.5] MoodCam: Mood Prediction Through Smartphone-Based Facial Affect Analysis in Real-World Settings
IEEE International Conference on Ubiquitous Intelligence and Computing (UIC 2024)

[C.3] MoodPupilar: Predicting Mood Through Smartphone Detected Pupillary Responses in Naturalistic Settings
IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks (BSN 2024)



[W.1] Revolutionizing Mental Health Support: An Innovative Affective Mobile Framework for Dynamic, Proactive, and Context-Adaptive Conversational Agents
ACM IMWUT/Ubicomp 2023, GenAI4PC Symposium

[Po.3] Towards Designing Empathetic and Trustworthy AI Chatbots: an Exploratory Study
CESUN 2023
Substance use sensing
Alcohol and cannabis intoxication from passive sensor data, with just-in-time interventions.
[J.7] Enhancing Interpretable, Transparent, and Unobtrusive Detection of Acute Marijuana Intoxication in Natural Environments: Harnessing Smart Devices and Explainable AI to Empower Just-In-Time Adaptive Interventions: Longitudinal Observational Study
JMIR AI 2025

[Po.4] Moving Toward Personalized Behavioral Medicine: Integrating Smartphone-based GPS Data into a Digital Alcohol Intervention
Society of Behavioral Medicine/Annals of Behavioral Medicine 2024
[J.4] Leveraging Mobile Phone Sensors, Machine Learning, and Explainable Artificial Intelligence to Predict Imminent Same-Day Binge-drinking Events to Support Just-in-time Adaptive Interventions: Algorithm Development and Validation Study
JMIR Formative Research 2023
.avif)
[J.3] Mobile phone sensor-based detection of subjective cannabis intoxication in young adults: A feasibility study in real-world settings
Drug and Alcohol Dependence 2021
Clinical movement
Gait and pose analysis for cerebral palsy and cognitive decline, run on a phone.
[J.9] AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computingTo appear
PLOS ONE 2026 (Under Review)
[J.8] Wearable Sensing for Quantifying Cognitive and Balance Functions in Naturalistic Movements of Older Adults with Mild Cognitive Impairment in Therapeutic EnvironmentsTo appear
PLOS Digital Health 2026 (* = Equal Contribution, Under Review)
[C.7] Clinically Accessible 2D Video Analysis Accurately Captures 3D Knee Gait KinematicsTo appear
Annual Meeting of the American Academy for Cerebral Palsy and Developmental Medicine (AACPDM 2026, Under Review)
[C.6] Evaluating the Feasibility of Deploying Quantized Human Pose Estimation on Smartphone for Gait Analysis for Children with Cerebral Palsy
Annual Meeting of the Gait & Clinical Movement Analysis Society (GCMAS 2026)
Eye & biometrics
Iris, pupil and gaze — for identity, and for what the eye gives away.

[J.2] EyeSpyVR: Interactive Eye Sensing Using Off-the-Shelf, Smartphone-Based VR Headsets
ACM IMWUT/Ubicomp 2018

[J.1] Convolutional neural networks for ocular smartphone-based biometrics
Pattern Recognition Letters, Volume 91. 2017

[C.1] A Preliminary Study of CNNs for Iris and Periocular Verification in the View Spectrum
ICPR 2016
HCI & systems
Interaction techniques and the tooling underneath — including the dubbing work behind AstraClips.
[C.8] XDubber: Supporting Non-Native Creators with Explainable Cross-Lingual Video DubbingTo appear
ACM UIST 2026 (Under Review)
[C.4] MotionTrace: IMU-based Trajectory Prediction for Smartphone AR Interactions
IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks (BSN 2024)

[Po.2] MicroFlow: Advancing Affective States Detection in Learning Through Micro-Expressions
CESUN 2023

