A two-stage webly-supervised pipeline that learns appearance from web images then motion from web videos with adversarial domain adaptation and attention reaches 74.9% on UCF-101 without curated training labels.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Image to Video Domain Adaptation Using Web Supervision
A two-stage webly-supervised pipeline that learns appearance from web images then motion from web videos with adversarial domain adaptation and attention reaches 74.9% on UCF-101 without curated training labels.