Learning to Answer Visual Questions from Web Videos. (arXiv:2205.05019v1 [cs.CV])

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