An information compressor in a pale blue dot.

Pau Rodríguez López

PhD researcher on AI and Computer Vision.
Research Scientist at Element AI Montreal.


2015 - 2019

PhD researcher

Computer Vision Center, Universitat Autònoma de Barcelona
On bio-inspired machine learning techniques applied to computer vision and social media.
2014 - 2015

Advanced master of Artificial Intelligence

KU Leuven
Magna Cum Laude. Topics: Artificial Neural Networks, Machine learning, SVM, Data Mining, Cybernetics and more.
2009 - 2014

Computer Engineering (5 years)

Universitat Autònoma de Barcelona
With honors. Topics: Artificial Intelligence, Networks, HPC and more.

Work Experience

June 2019 - present

Research Scientist

Element AI, Montreal
Metalearning, Computer Vision
Feb 2018 - Feb 2019

Research Internship

Element AI, Montreal.
Unsupervised Deep Learning and Uncertainty.
May 2014 - Aug. 2014

Research Assistant

Visual Tagging Services, Computer Vision Center, Universitat Autònoma de Barcelona.
Developing learning algorithms for image classification.
Oct 2013 - May 2014

Research Assistant

Universitat Autònoma de Barcelona
Engineering on large scale image classification and retrieval with deep learning techniques.
Jun. 2013 - Oct. 2013

Member of the Chalearn Organization Committee

Computer Vision Center, Universitat Autònoma de Barcelona
Research assistant, organizing the human gesture databases used in the ChaLearn Multimodal Gesture Recognition Challenge 2013, and in the ChaLearn Looking at People 2014, co-organized by CVC, UAB, UB, UOC, Coplinet (California) and Microsoft.
Sep. 2012

Research Assistant

Department of Information and Communications Engineering, Universitat Autònoma de Barcelona.
Extending proposal of standard for the Consultative Commitee for Space Data Systems for the Group on Interactive Coding of Images. Working over an implementation based on the Nasa’s CSSDS-122 Public Release Version.


Jun. 2015

MASTER THESIS - Reducing Redundancy in Convolutional Neural Networks

Director: Prof. Bart de Moor / Supervisor: Peter Roelants
Successfuly reduced the redundancy of CNNs by prunning redundant filters.
Jun. 2014

DEGREE THESIS - A Big Data approximation with deep neural networks

Computer Science department, Universitat Autònoma de Barcelona
Director: Jordi Gonzàlez Sabaté / Supervisor: Pep Gonfaus
Designed and deployed a deep learning system for big data applications.

Awards and merits


Google Summer of Code

tiny-dnn - OpenCV
Include recurrent neural networks in the tiny-dnn framework.

FI Doctoral scholarship

Government of Catalonia
Government fundings for the PhD studies.

PIF Doctoral scholarship

Universitat Autònoma de Barcelona

First-of-class honours

Universitat Autònoma de Barcelona
Distinction for the best grade in the class.

Kaggle Galaxy Zoo
15th out of +300, signed as prlz77.
May 2014 - Aug. 2014

Santander Grants for SME Internships

Santander Bank
For an internship in Visual Tagging Services.
May 2014

Scholarship for collaboration in a University department.

Spanish Ministry of Education

Teaching and Seminars


Computer Vision and AI seminar

Parc de Recerca, UAB

AI4ALL Computer Vision and AI lab

Engineering school, UAB
Sept. 28th 2018

How do machines learn?

CosmoCaixa (Nit de la recerca), Barcelona

Machine Learning lab (Computer Engineering)

Engineering school, UAB

Machine Learning seminars (Computer Engineering)

Engineering school, UAB

Programming methodology labs (Computer Engineering)

Engineering school, UAB
Oct. 14th 2015

Deep learning 101

Vall d'Hebron Research Institute (VHIR), Barcelona

Other courses


Machine Learning

Coursera - Standford, Andrew NG.


Journals IEE TM2019, IMAVIS2019, TPAMI2017, PR(SI-AMDO)2017
Conferences MAIS2019, NeurIPS2016


  1. Lopez, P. R., Dorta, D. V., Preixens, G. C., Sitjes, J. M. G., Marva, F. X. R., & Gonzalez, J. (2019). Pay attention to the activations: a modular attention mechanism for fine-grained image recognition. IEEE Transactions on Multimedia.
  2. Rodriguez, P., Gonfaus, J. M., Cucurull, G., XavierRoca, F., & Gonzalez, J. (2018). Attend and Rectify: a gated attention mechanism for fine-grained recovery. In ECCV.
  3. Rodrı́guez Pau, Gonzàlez, J., Cucurull, G., Gonfaus, J. M., & Roca, X. (2017). Regularizing CNNs with Locally Constrained Decorrelations. In ICLR.
  4. Oreshkin, B. N., Rodriguez, P., & Lacoste, A. (2018). TADAM: Task dependent adaptive metric for improved few-shot learning. In NIPS.
  5. Negin, F., Rodriguez, P., Koperski, M., Kerboua, A., Gonzàlez, J., Bourgeois, J., … Bremond, F. (2018). PRAXIS: Towards automatic cognitive assessment using gesture recognition. Expert Systems with Applications, 106, 21–35.
  6. Bellantonio, M., Haque, M. A., Rodriguez, P., Nasrollahi, K., Telve, T., Escarela, S., … Anbarjafari, G. (2016). Spatio-Temporal Pain Recognition in CNN-based Super-Resolved Facial Images. In International Conference on Pattern Recognition (icpr). Springer.
  7. Rodrı́guez Pau, Cucurull, G., Gonfaus, J. M., Roca, F. X., & Gonzàlez, J. (2017). Age and Gender Recognition in the Wild with Deep Attention. Pattern Recognition.
  8. Rodriguez, P., Cucurull, G., Gonzàlez, J., Gonfaus, J. M., Nasrollahi, K., Moeslund, T. B., & Roca, F. X. (2017). Deep Pain: Exploiting Long Short-Term Memory Networks for Facial Expression Classification. IEEE Transactions on Cybernetics.