Building intelligent systems that understand people in context
I am a Royal Academy of Engineering Research Fellow in the Department of Engineering at King's College London, and an hourly paid Lecturer in Computer Vision at the Department of Informatics. My research combines computer vision, multimodal machine learning, and explicit reasoning to build socially intelligent systems that understand human behaviour in context.
I received my PhD in Engineering and Applied Sciences from the University of Barcelona, where I worked on eye tracking with spatiotemporal and multimodal deep learning for remote and wearable cameras. I also hold an MSc in Artificial Intelligence and a BEng in Audiovisual Telecommunications Systems from the Polytechnic University of Catalonia.
Across academia and industry, including the Computer Vision Center, Noldus IT, and Meta, I have worked on human behaviour understanding and synthesis for robotics, virtual agents, and extended reality.
Research interests
- Context-aware social AI
- Multimodal human behaviour understanding
- Hybrid and neuro-symbolic AI
- Human motion generation
- Gaze and eye tracking
- Social robotics
Latest news
All news →UDIVA HHOI at ECCV 2026. The challenge and CONTEXTUS workshop brought together research on understanding human interaction in context.
Best Talk at MultimodalAI 2026. Recognition for the presentation of UDIVA HHOI and its approach to multimodal interaction understanding.
Royal Academy of Engineering Research Fellowship. Awarded a five-year fellowship to develop ECASIS.