Research interests
- Human behaviour analysis
- Data mining
- Medical image analysis
- Convolutional neural networks and deep learning
- Pattern recognition
- Autonomous health monitoring systems
- Video understanding
Wanting to collaborate?
You can always reach me at e(dot)talaveramartinez(at)utwente(dot)nl
You can also connect via Linkedin or Twitter.
Starting a PhD?
If you have pre-secured a fellowship/scholarship paying your own salary or intend to apply for one, and your research interests match any of the above topics, then please feel free to send me an email.
Datasets
EgoFoodPlaces - Food related scenes in egocentric photo-streams
Martinez, Estefania Talavera, Maria Leyva-Vallina, Md Mostafa Kamal Sarker, Domenec Puig, Nicolai Petkov, and Petia Radeva. “Hierarchical approach to classify food scenes in egocentric photo-streams.” IEEE journal of biomedical and health informatics 24, 2019.
EgoRoutine - Routine related human behaviour in egocentric photo-streams
Talavera, Estefania, Carolin Wuerich, Nicolai Petkov, and Petia Radeva. “Topic modelling for routine discovery from egocentric photo-streams.” Pattern Recognition 104, 2020.
InstaIndoor - Indoor scene recognition in videos gathered from social media
Paper, GitHub with code and dataset
A. Glavan, E. Talavera, “InstaIndoor and multi-modal deep learning for indoor scene recognition”, Neural Computing and Applications, 2022.
HR-Crime - Human related crime in surveillance fideos
K. Boekhoudt, A. Matei, M. Aghaei, E. Talavera, “HR-Crime: Human-related anomaly detection in surveillance videos”, 19th Conference on Computer Analysis of Images and Patterns (CAIP), 2021.