Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading
Open paper
Benchmark
Model
Rank
Results
lipreading-on-lip-reading-in-the-wild
PCPG
–
Top-1 Accuracy: 83.5
lipreading-on-lrw-1000
PCPG
–
Top-1 Accuracy: 38.7%
Rank counts only results with a code link.