A temporal compositional modular network that decomposes queries into main event, context event, and temporal signal improves video moment localization on TEMPO.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploiting Temporal Relationships in Video Moment Localization with Natural Language
A temporal compositional modular network that decomposes queries into main event, context event, and temporal signal improves video moment localization on TEMPO.