Hi! I am Makarand Tapaswi, a PostDoctoral Fellow at the Machine Learning group, University of Toronto, working with Prof. Sanja Fidler.
Broadly, my work revolves around the vision and language sub-field. In particular, I enjoy working with movies and TV series, especially teaching machines about human behavior and analyzing storylines.
Previously, I was a PhD student and Research Assistant at the Computer Vision for Human Computer Interaction (CVHCI) lab, Karlsruhe Institute of Technology, Germany. I introduced novel problems such as alignment of books with movies, plot synopses (from Wikipedia) with TV episodes, their visualization inspired by XKCD, and the first story question-answering challenge: MovieQA. I also worked on clustering and identifying characters in videos to allow for semantic video analysis.
If you have any questions, please feel free to contact me.
Movie4D: Understanding special effects in movies; MovieGraphs: Understanding human interactions, emotions, relationships, over time in movies.
On predicting detailed content of images (situations) including the action, and related information such as agent, place, and other roles depending on the action.