Web: http://arxiv.org/abs/2205.05019

May 11, 2022, 1:10 a.m. | Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev, Cordelia Schmid

cs.CV updates on arXiv.org arxiv.org

Recent methods for visual question answering rely on large-scale annotated
datasets. Manual annotation of questions and answers for videos, however, is
tedious, expensive and prevents scalability. In this work, we propose to avoid
manual annotation and generate a large-scale training dataset for video
question answering making use of automatic cross-modal supervision. We leverage
a question generation transformer trained on text data and use it to generate
question-answer pairs from transcribed video narrations. Given narrated videos,
we then automatically generate the …

arxiv cv learning videos web

More from arxiv.org / cs.CV updates on arXiv.org

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote

Director of AI/ML Engineering

@ Armis Industries | Remote (US only), St. Louis, California

Digital Analytics Manager

@ Patagonia | Ventura, California