issues
search
evonneng
/
learning2listen
Official pytorch implementation for Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion (CVPR 2022)
105
stars
10
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to predict 32 to 64 frames of the speaker when 40 frames of speaker information are input during training
#17
lsy492
opened
2 months ago
1
where can I download the original videos?
#16
tanshuai0219
closed
6 months ago
1
Render
#15
wzx7084
closed
6 months ago
1
Raw audio
#14
yoolish
closed
6 months ago
1
RE. Unable to reproduce audio 128-D mel spectrogram feature from raw video
#13
nguyenntt97
opened
1 year ago
2
Render the output of this project to DECA
#12
FortisCK
closed
1 year ago
1
Mismatch in face features size between paper and the code release
#11
nguyenntt97
closed
1 year ago
0
How long does it usually takes for training the classifier?
#10
Daksitha
closed
1 year ago
2
Restarting Vqgan training from checkpoint break the training loss
#9
Daksitha
closed
1 year ago
1
Abrupt Jumps in listener expression
#8
rohitkatlaa
opened
1 year ago
8
vqgan training and validation loss
#7
Daksitha
closed
1 year ago
1
How to render the output of this project to DECA
#6
liangyishiki
closed
1 year ago
1
Runtime error during training the predictor model
#5
leyi-123
closed
1 year ago
1
Usage of List of Files
#4
Daksitha
closed
1 year ago
1
Reconstructing generated output
#3
rohitkatlaa
closed
1 year ago
3
Why exactly 4T in extracting Mels?
#2
Daksitha
closed
1 year ago
4
About the vq loss when training the codebook
#1
wangzheng1209
closed
1 year ago
1