I am an Associate Professor at University of Toronto, and a Director of AI at NVIDIA, leading a research lab in Toronto. Prior coming to Toronto, in 2012/2013, I was a Research Assistant Professor at Toyota Technological Institute at Chicago, an academic institute located in the campus of University of Chicago. I did my postdoc with Prof. Sven Dickinson at University of Toronto in 2011/2012. I finished my PhD in 2010 at University of Ljubljana in Slovenia in the group of Prof. Ales Leonardis. In 2010, I was visiting Prof. Trevor Darrell's group at UC Berkeley and ICSI. I got my BSc degree in Applied Math at University of Ljubljana. More information is in my CV.

I'm looking for motivated MSc/PhD and visiting students, as well as a postdoc.


My work is in the area of Computer Vision. My main research interests are 2D and 3D object detection, particularly scalable multi-class detection, object segmentation and image labeling, and (3D) scene understanding. I am also interested in the interplay between language and vision: generating sentential descriptions about complex scenes, as well as using textual descriptions for better scene parsing (e.g., in the scenario of the human-robot interaction).


Program Chair:3DV'16
Area Chair:
       Computer Vision:ECCV'18, CVPR'18, ICCV'17, CVPR'17, CVPR'16, ACCV'16
       Machine Learning:ICLR'18, NIPS'17, ICLR'17
       NLP:EMNLP'17, EMNLP'16
       AI:AAAI'18
Chair:Tutorial Chair (CVPR'16), Publications co-Chair (CVPR'13, CVPR'14, CVPR'15, ICCV'15), Presentations Chair (CVPR'10)
Program Committee:CVPR'09-'15, ECCV '08-'16, NIPS'13-'16, ACCV'09, ICRA'15, IROS'15


Tutorial:3D Indoor Scene Understanding, a half-day tutorial at CVPR'15, co-organized with Raquel Urtasun
Workshops:Role of Simulation in Computer Vision, Workshop at ICCV'17
The Joint Video and Language Understanding Workshop: MovieQA and The Large Scale Movie Description Challenge, Workshop at ICCV'17
Geometry Meets Deep Learning, Workshop at ICCV'17
Geometry Meets Deep Learning, Workshop at ECCV'16
RMRC Challenge, Workshop at ECCV'14
RMRC Challenge, Workshop at ICCV'13


Paper award:Best paper honorable mention at CVPR'17

Faculty award:Connaught Innovation Award, 2020
Early Researcher Award, 2019
Canada CIFAR AI Chair, 2018
Connaught New Researcher Award, 2018
Amazon Academic Research Award, 2017
NVIDIA Pioneer of AI Award, 2016
Facebook Faculty Award, 2016

Reviewing:Outstanding reviewer award at ECCV'08, ECCV'12, CVPR'12, CVPR'15

Teaching:Professor of the Year, 2014/2015, awarded by the UofT's Computer Science Student Union
Best Teaching Assistant, 2007, awarded by University of Ljubljana's Computer Science Student Union

Other:Best student presentation at EU Cognition's student competition, 2007
Best paper award at Austrian Association for Pattern Recognition (AAPR) conference, 2003
Thesis Award for Diploma (BSc) Thesis, University of Ljubljana, Math & Physics Dept


What I like perhaps the most about academic life is working with students -- seeing them develop and helping them succeed. I particularly want to inspire and encourage (through talks and competitions) the younger generations to pursue graduate studies in Computer Science.


Competitions:Research video competition for undergraduate students (UofT's summer research program), 2015
Research video competition for undergraduate students, 2014
Multimedia Chair for International Mathematical Olympiad (high school students), 2006

Talks:Talk at TEDxUofT, 2017
Invited talk for the UofT undergradute students' AI Day'16
Talk on "The Gee-Whiz of A.I. at UofT", grad orientation day for CogSci students
Talk on "How to write a research paper", USRA'16, UofT
Invited talk at the Women in Computer Vision workshop in conjunction with CVPR'15, intended to mentor female graduate students
Talk on "How to make a research video", USRA'15, UofT
Invited talk for the UofT undergradute students' AI night'14
Invited lecture for high school students, Math summer school MARS in Slovenia, 2014
Talk on "How to make a research video", USRA'14, UofT


back to top


► Our pop song generator was picked up by the media:



► The MovieQA benchmark was featured in the media:


► Our work on fashionability received a lot of attention in the press:





A more complete list is maintained on our project webpage.


back to top