A two-branch 2D/3D CNN with attention fusion and a bidirectional ConvLSTM yields a marginal LRW accuracy gain, but its LRW-1000 score is below the cited state of the art.
Lrw-1000: A naturally-distributed large-scale benchmark for lip reading in the wild
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Multi-Grained Spatio-temporal Modeling for Lip-reading
A two-branch 2D/3D CNN with attention fusion and a bidirectional ConvLSTM yields a marginal LRW accuracy gain, but its LRW-1000 score is below the cited state of the art.