Fine-grained Instructional Video undERstanding Workshop Call for Papers
Fine-grained Instructional Video undERstanding Workshop
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:
- Datasets and benchmarks;
- New methods, algorithms and models;
- Position papers;
- Ideas for challenge problems; what datasets are needed?
Abstracts can be submitted at http://fiver.eecs.umich.edu/submit 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
More information: http://fiver.eecs.umich.edu/callforabstracts