Oriol Pujol

Oriol Pujol

Oriol Pujol
PhD in Computer Science, from Autonomous University of Barcelona
Associate Professor at Universitat de Barcelona

Personal webpage

email: oriol_pujol@ub.edu

Biosketch

Oriol Pujol Vila obtained the degree in Telecomunications Engineering in 1998 from the Universitat Politècnica de Catalunya (UPC). The same year, he joined the Computer Vision Center and the Computer Science Department at Universitat Autònoma de Barcelona (UAB). In 2004 he received the Ph.D. in Computer Science at the UAB on work in deformable models, fusion of supervised and unsupervised learning and intravascular ultrasound image analysis. In 2005 he joined the Dept. of Matemàtica Aplicada i Anàlisi at Universitat de Barcelona (UB) where he obtained the permanent position of associate professor. He has been since 2004 an active member in the organization of several activities related with machine learning, computer vision, and artificial intelligence

Current and previous positions:

  • Head of Computer Science Undergraduate Studies at Universitat de Barcelona
  • Director of the Data Science and Big Data Postgraduate Course
  • Coordinator of the Vision and Computational Learning research group.

Research Interests

  • Machine Learning
  • Computer Vision
  • Artificial Intelligence
  • Data Science
  • Signal and Image Processing

Selected publications

  •  Segui, O. Pujol, J. Vitrià, “Learning to Count with Deep Object Features”, IEEE Int. Conf. On Computer Vision and Pattern Recognition, 2015.
  • Gatta, E. Puertas, O. Pujol, “Multi-scale stacked sequential learning”, Pattern Recognition, 44 (10), 2011.
  • Escalera, O. Pujol, P. Radeva, “On the decoding process in ternary error-correcting output codes”, IEEE Trans. On Pattern Analysis and Machine Intelligence, 32 (1), 2010.
  • Pujol, D. Masip, “Geometry-based ensembles: toward a structural characterization of the classification boundary”, IEEE Trans. On Pattern Analysis and Machine Intelligence, 31 (6), 2009.
  • Pujol, P. Radeva, J. Vitrià, “Discriminant ECOC: A heuristic method for application dependent design of Error Correcting Output Codes”, IEEE Trans. On Pattern Analysis and Machine Intelligence, 28 (6), 2006.