Fine-grained Instructional Video undERstanding

FIVER is a half-day workshop to be held at CVPR 2018

Video understanding has advanced quite a long way in the past decade, moving from classifying easily segmented human activity on static backgrounds and tracking single objects smoothly moving without clutter to large-scale detection and segmentation of action amidst dense clutter and translation of video into textual description automatically, to name a few.  In this workshop, we will take a step beyond these individual video understanding problems and begin a conversation surrounding the nascent problem area of learning from instructional video.  

The goal of this workshop is to start a conversation around learning from instructional video with the ultimate plan to organize a future, longer-scale workshop with one or more challenge problems.  To that end, we invite submissions of abstracts along the following topics in the context of learning from instructional video and fine-grained video understanding:

Abstracts can be submitted at and should be 1-2 page pdfs in the standard CVPR format.  Abstracts are not papers and will not be a part of any proceedings; we hence welcome accepted CVPR 2018 papers.  Our goal is to get as many community members as possible into the discussion.  Selected abstracts will be invited to present a poster during the workshop.  A subset of selected abstracts will be invited to give a talk and/or participate as panelists in the discussion near the end of the workshop.

Abstracts Due April 15, 2018

Workshop Organizers

Jason Corso

University of Michigan

Josef Sivic

INRIA and Czech Technical University   

Ivan Laptev


Luowei Zhou

University of Michigan

For more information, contact