CVPR'17 Workshop on YouTube-8M Large-Scale Video Understanding Call for Papers
CVPR'17 Workshop on YouTube-8M Large-Scale Video Understanding
We invite researchers to participate in a large-scale video
classification challenge and to report their results at this workshop,
as well as to submit papers describing research, experiments, or
applications based on the YouTube-8M video dataset. The dataset was
created from over 450,000 hours of video, spanning over 20 diverse
video domains. In order to facilitate both academic institutions and
industry participation, we are providing video-level and frame-level
image and audio features extracted at a rate of one frame per second
for 7 million YouTube videos, which should enable researchers to train
machine learning classification models at this scale within days. In
parallel we are also running a Kaggle challenge on this dataset with a
first prize of $30,000. For more details, see the workshop website and
blog post.
Paper Submission Deadline June 16, 2017
Paper Camera-Ready Deadline July 14, 2017
Workshop date (co-located with CVPR'17) July 26, 2017