David Masip is professor in the Computer Science Department, Universitat Oberta de Catalunya since February 2007. He is the director of the SUNAI (Scene Understanding and Artificial Intelligence) research group. He is member of the BCN Perceptual Computing Lab. He studied Computer Science in the Universitat Autonoma de Barcelona, obtaining a FPI grant in 2001 for starting his PhD degree in the Computer Vision Center (Spain). He obtained the PhD degree in September 2005. He obtained the best Thesis award on Computer Science in the Universitat Autònoma de Barcelona.
David Masip’s main research interest is the application of computer vision and pattern recognition to solve problems. David is interested in general machine learning algorithms, with special interest in Deep Learning algorithms and their applications to vision technologies. Particularly David is always open to collaborate with colleagues, and currently he is working on several research projects:
- Facial expression analysis and its applications to automated emotion perception in humans. Emotions play an important role in our everyday lives. The automated log of emotions has proved to be especially useful in medical applications (in depression or autism treatment and monitoring). We are currently collaborating with several organizations to provide SW solutions to specific problematics in the facial expression analysis field.
- Animal tracking. With the recent advances in brain imaging, it became feasible to record large images databases of mice in vivo. This vast amount of data can correlate the neural responses and the visible behavior of the animal. We are designing specific algorithms for mice movement tracking and its applications to neuroscience.
- Sea animal behavior monitoring. Currently, there exist a huge amount of video recordings of several fish species interacting in a controlled environment. The use of automated tracking and behavior understanding will help biologists to understand the hidden patterns of activity of species.
Interpreting CNN Models for Apparent Personality Trait Regression Inproceedings
Computer Vision and Pattern Recognition Workshops (CVPRW), 2017 IEEE Conference on, IEEE, 2017.
Emotion recognition from mid-level features Journal Article
Pattern Recognition Letters, 67 , pp. 66–74, 2015.
Online error correcting output codes Journal Article
Pattern Recognition Letters, 32 (3), pp. 458-467, 2011.
On the use of Monte Carlo simulation, cache and splitting techniques to improve the Clarke and Wright savings heuristics Journal Article
Journal of the Operational Research Society, 2010.
Geometry-Based Ensembles: Toward a Structural Characterization of the Classification Boundary Journal Article
IEEE Transactions on Pattern Analysis and Machine Intelligence, 31 , pp. 1140–1146, 2009.
Boosted Online Learning for Face Recognition Journal Article
IEEE Transactions on Systems Man and Cybernetics part B, 39 , pp. 530–538, 2009.
Enabling Automatic Just-in-time Evaluation of In-class Discussions in On-line Collaborative Learning Practices. Journal Article
Journal of Digital Information Management (JDIM), 7 , pp. 290-297, 2009.
Preferred Spatial Frequencies for Human Face Processing Are Associated with Optimal Class Discrimination in the Machine Journal Article
PLoS ONE, 3 (7), pp. e2590, 2008.
Shared Feature Extraction for Nearest Neighbor Face Recognition. Journal Article
IEEE TRANSACTIONS ON NEURAL NETWORKS, 19 (4), pp. 586-595, 2008.
A sparse Bayesian approach for joint feature selection and classifier learning Journal Article
Pattern Anal. Appl., 11 (3-4), pp. 299–308, 2008, ISSN: 1433-7541.
Boosted discriminant projections for nearest neighbor classification Journal Article
Pattern Recognition, 39 (2), pp. 164-170, 2006.
On the Use of External Face Features for Identity Verification. Journal Article
JOURNAL OF MULTIMEDIA, 1 (4), pp. 11-20, 2006.
An ensemble-based method for linear feature extraction for two-class problems Journal Article
Pattern Anal. Appl., 8 (3), pp. 227-237, 2005.
Feature extraction methods for real-time face detection and classification Journal Article
EURASIP J. Appl. Signal Process., 2005 (1), pp. 2061–2071, 2005, ISSN: 1110-8657.
Feature extraction for nearest neighbor classification: Application to gender recognition Journal Article
Int. J. Intell. Syst., 20 (5), pp. 561-576, 2005.