About Me
Hello! I am Nerea Gallego, a Computer Science PhD Candidate at the University of Zaragoza, currently working within the Robotics, Computer Vision and AI Group (RoPert) supported by a DGA Fellowship.
My research revolves around a central question: How can we help machines understand complex human behaviors using multiple sensors? Specifically, I specialize in multimodal learning, open-vocabulary Vision-Language Models (VLMs), and event-based vision. I am passionate about applying these cutting-edge AI technologies to solve real-world challenges, particularly in the medical field, such as improving patient monitoring in sleep studies through neuromorphic cameras to preserve privacy and work in low-light conditions.
Beyond the code and the lab, I am a strong advocate for making technology accessible. Whether I am co-supervising undergraduate theses, sharing my knowledge as a STEM tutor, or volunteering for the "Girls' Day" to inspire the next generation of women in engineering, I believe that the true power of AI lies in its community and its positive impact on society.
My current focus areas:
- Multimodal Human Behavior Inference: Understanding social interactions and multi-agent dynamics in videos.
- Neuromorphic Vision in Healthcare: Developing architectures like EventSleep2 for full-night clinical monitoring.
- STEM Outreach: Bridging the gap between complex AI concepts and young minds.
Resume
Education
Experience
Grants & Awards
-
PhD Fellowship (DGA)
Competitive predoctoral contract awarded by the Government of Aragon to fund PhD research in Computer Vision.
-
Best Bachelor Thesis Award
Recognized by NTT DATA for excellence in research and technical development within the field of AI.
-
Research Initiation Grant (I3A)
Early-stage research grant awarded by the Aragon Institute of Engineering Research for academic excellence.
-
Research Initiation Grant (I3A)
Grant for an initial research stay to develop foundational skills in the Robotics and AI Group.
Languages
Tech Stack & Expertise
Publications & Projects
TIMID: Time-Dependent Mistake Detection in Videos of Robot Executions
Nerea Gallego*, Fernando Salanova*, Claudio Mannarano, Cristian Mahulea, Eduardo Montijano
Introduced a novel framework for identifying temporal mistakes in robotic tasks. By leveraging time-dependent analysis, we achieved high-precision detection of execution errors that traditional frame-by-frame models often overlook.
EventSleep2: Sleep activity recognition on complete night sleep recordings with an event cameras
Nerea Gallego*, Carlos Plou*, Miguel Marcos, Pablo Urcola, Luis Montesano, Eduardo Montijano, Ruben Martinez-Cantin, Ana C. Murillo
Introduced an advanced neuromorphic architecture designed for long-term temporal consistency in event-based vision. Managed the acquisition and processing of full-night clinical datasets, overcoming data dimensionality challenges to enable open-vocabulary sleep activity recognition.
Vision-based feedback on correct sensor placement in medical studies
Nerea Gallego, Carlos Plou, Luis Montesano, Ana C. Murillo, Eduardo Montijano
Developed a real-time visual feedback system to assist in the precise placement of EEG sensors. Designed human-in-the-loop protocols and executed multi-subject data collection to ensure system robustness across different physiological profiles.
EventSleep: Sleep activity recognition with event cameras
Carlos Plou, Nerea Gallego, Alberto Sabater, Eduardo Montijano, Pablo Urcola, Luis Montesano, Ruben Martinez-Cantin, Ana C. Murillo
Introduced the first EventSleep architecture for sleep monitoring using neuromorphic vision. Created a novel, high-dimensionality event dataset to address the limitations of traditional cameras in low-light and privacy-sensitive clinical environments.
Contact
Feel free to reach out to me via email or connect with me on professional networks.