WSLLN trains a two-branch alignment and selection network with video-level sentence matching plus self-generated pseudo segment labels, and reports state-of-the-art weakly supervised temporal language localization on two benchmarks.
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
-
WSLLN: Weakly Supervised Natural Language Localization Networks
WSLLN trains a two-branch alignment and selection network with video-level sentence matching plus self-generated pseudo segment labels, and reports state-of-the-art weakly supervised temporal language localization on two benchmarks.