BMN uses a boundary-matching mechanism to generate precise temporal action proposals with reliable confidence scores simultaneously in an end-to-end framework, improving results on THUMOS-14 and ActivityNet-1.3.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
BMN uses a boundary-matching mechanism to generate precise temporal action proposals with reliable confidence scores simultaneously in an end-to-end framework, improving results on THUMOS-14 and ActivityNet-1.3.