A context-aware zero-shot learning model predicts novel crowd behavior attributes by weighting known-attribute video classifiers with word-vector co-occurrence estimates, improving over prior zero-shot baselines.
Learning multi-label scene classification
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
-
Zero-Shot Crowd Behavior Recognition
A context-aware zero-shot learning model predicts novel crowd behavior attributes by weighting known-attribute video classifiers with word-vector co-occurrence estimates, improving over prior zero-shot baselines.