IFT 6765 - Links between Computer Vision and Language

Guidelines for paper presentations
(Guidelines credits: Self-supervised Representation Learning course taught by Aaron Courville at UdeM, Advanced Computer Vision course taught by Devi Parikh at Virginia Tech)

Each student will present twice in the whole course. Both presentations will be on the topic of that day. Students can choose to present multiple papers – excluding the review paper, as everyone would have read it. Each presentation should be maximum 40 minutes long (25 mins presentation + 15 mins discussion and Q&A). Students should practice their talks in advance to make sure the timing is right.

The presentation should include a novel synthesis of the material – the idea is for you to teach that topic to the class. Slides and lecture notes are to be made available on the course website. The presentation of novel experiments exploring and reproducing the methods is encouraged but not strictly required.  Lectures should include the following: