Dr. Miguel Angel Bautista

Bio

I recently earned my Ph. D in Error-Correcting Representation for Multi-class problems at University of Barcelona. My main research are Computer Vision, Pattern Recognition, Optimization and its applications in real-world problems. I received my B. Sc. and M. Sc. degrees in Computer Science and Artificial Intelligence from Universitat de Barcelona and Universitat Politécnica de Catalunya in January and June 2010, respectively. From 2010 to 2015 I was a research member at the Computer Vision Center and at the Applied Mathematics and Analysis Dept. at Universitat de Barcelona . In 2010 I received the first prize award from the Catalan Association of Artificial Intelligence Thesis Awards. In 2013 I was a visitor at Carnegie Mellon University (advised by Dr. Fernando de la Torre), funded by the AGAUR-BE grant.

Current Projects

• Deep similarity learning

• Drivable surface detection

• Human Pose Recovery using contextual representations

• Error-Correcting Networks

Publications

JOURNALS

• Error-Correcting Factorization. Miguel Angel Bautista, Oriol Pujol, Fernando De la Torre and Sergio Escalera. IEEE Transactions on Pattern Analysis and Machine Intelligence, Under review, 2015.

• A Gesture Recognition System for Detecting Behavioral Patterns of ADHD. Miguel Angel Bautista, Antonio Hernandez-Vela, Sergio Escalera, Laura Igual, Oriol Pujol, Josep Moya, and Veronica Violant, and Marıa Teresa Anguera. IEEE Transactions on Systems, Man and Cybernetic Part B, 2015.

• HuPBA 8k+: Dataset and ECOC-GraphCut based Segmentation of Human Limbs. Daniel Sanchez, Miguel Angel Bautista, and Sergio Escalera. Neurocomputing, 2014, Elsevier.

• On the design of an ECOC-compliant genetic algorithm. Bautista, Miguel Angel and Escalera, Sergio and Baro, Xavier and Pujol, Oriol. Pattern Recognition, 47, 2, 865–884, 2013, Elsevier.

• Probability-based Dynamic Time Warping and Bag-of-Visual-and-Depth-Words for Human Gesture Recognition in RGB-D. Hernandez-Vela, Antonio and Bautista, Miguel Angel and Perez-Sala, Xavier and Ponce-Lopez, V ́ıctor and Escalera, Sergio and Baro, Xavier and Pujol, Oriol and Angulo, Cecilio. Pattern Recognition Letters, 2013, Elsevier.

• Minimal Design of Error-Correcting Output Codes. Bautista, M. A. and Escalera, S. and Baro, X. and Radeva, P. and Vitria, J. and Pujol, O. Pattern Recognition Letters, 33, 6, 693–702, 2012, Elsevier.

CONFERENCES

• Learning to Segment Humans by Stacking their Body Parts. E. Puertas, MA. Bautista, D. Sanchez, S. Escalera and O. Pujol. European Conference on Computer Vision Workshops, 1, 2014.

• ChaLearn Looking at People Challenge 2014: Dataset and Results. S. Escalera, X. Baro, J. Gonzalez, M. A. Bautista, M. Madadi, M. Reyes, V. Ponce, H. J. Escalante, J. Shotton, I. Guyon. European Conference on Computer Vision Workshops, 2014.

• Human Body Segmentation with Multi-limb Error-Correcting Output Codes Detection and Graph Cuts Optimization. Sanchez, Daniel and Ortega, Juan Carlos and Bautista, Miguel Angel and Escalera, Sergio. Pattern Recognition and Image Analysis,50–58, 2013, Springer Berlin Heidelberg.

• A Genetic Inspired Optimization for ECOC. Bautista, M. A. Escalera, S. and X. and Baro, X. and Pujol, O. Structural, Syntactic, and Statistical Pattern Recognition, 743–751, Springer, 2012.

• Probability-based Dynamic Time Warping for Gesture Recognition on RGB-D data. Bautista, M. A, and Hernandez-Vela, A. and Ponce, V. and Perez-Sala, X. and Baro, X. and Pujol, O. and Angulo, C. and Escalera, S. Internation Conference on Pattern Recognition Workshops, 2012.

• BoVDW: Bag-of-Visual-and-Depth-Words for Gesture Recognition Hernandez-Vela, A. and Bautista, M. A. and Perez-Sala, X. and Ponce, V. and Baro, X. and Pujol, O. and Angulo, C. and Escalera, S. Proceedings of International Conference on Pattern Recognition, 449 -452, 2012.

• Introducing the separability matrix for error correcting output codes coding Bautista, M. A and Pujol, O. and Bar o, X. and Escalera, S. In Proc., Multiple Classifier Systems, 227–236, 2011, Springer.

• On the Design of Low Redundancy Error-Correcting Output Codes Bautista, M. A and Escalera, S. and Bar o, X. and Pujol, O. and Vitria, J. and Radeva, P. Ensembles in Machine Learning Applications, 21–38, 2011, Springer

• Compact evolutive design of error-correcting output codes. Bautista, M. A. and Baro, X. and Pujol, O. and Radeva, P. and Vitria, J. and Escalera, S. European Conference on Machine Learning Workshops, 119–128, 2010.