I am a M.Sc. student in Computer Science at the University of Toronto co-advised by Sanja Fidler and Raquel Urtasun. Previously I was a visiting student at MIT advised by Antonio Torralba, and I obtained B.Sc. degrees in Computer Science and Electrical Engineering from UPC BarcelonaTech, where I collaborated with LARCA.

I am interested in machine learning and its applications to computer vision and natural language processing. In particular, I am interested in understanding visual stories and learning in settings with weak supervision and cross-modal inputs.


Annotating Object Instances with a Polygon-RNN

L. Castrejón, K. Kundu, R. Urtasun, S. Fidler

CVPR 2017 (Oral)

Cross-Modal Scene Networks

Y. Aytar*, L. Castrejón*, C. Vondrick, H. Pirsiavash, A. Torralba

In submission

Learning Aligned Cross-Modal Representations from Weakly Aligned Data

L. Castrejón*, Y. Aytar*, C. Vondrick, H. Pirsiavash, A. Torralba

CVPR 2016


· [02/2017] Domain adaptation and Cross-Modal Scenes @ UofT CSC2539
· [12/2016] Cross-Modal Scene Representations @ UPC Barcelona, Prof. Xavi Giró group
· [02/2016] Tutorial on Domain adaptation and Zero-shot learning @ UofT CSC2523