Open Jhc-china opened 3 years ago
Hello, @Jhc-china , thanks for your questions. Here are my answers.
movement_inverval.csv
file. We define and collect 164 but the dancers did use all of them.@abcyzj Thanks for your fast reply very much! I have some further questions.
durations
part of the choreography file. Whether to split it or not depends on your implementation. In our paper, we split the 'HOLD' annotation by beats.@abcyzj Thanks again for your reply! I'm just curious about some implementation of CAU Prediction Model:
"the local music feature is set to 10 second"
and implement it by stacking five 1D-Conv layers. Is the kernel_size (local music reception field) for each 1D-Conv layer is 1000(frames) or just 200(frames)? Where the latter one, I think the reception field of last 1D-Conv layer can be equivalent to 1000 frames from input music feature.Algorithm 1
in your paper, the time-axis of training procedure is beat, which means I should shift the window by N beats according to the beat duration of predicted CAU. While the time-axis of input music feature is millisecond, I thought, 10ms gap between extracted music feature. To obtain the next encoded $m_{t}$, the window in music feature should shift by N * _beatinterval(in ms) / 10. Is that right? There maybe integer conversion in this transition but I think it doesn't matter?Thanks @abcyzj.
$m_{t}$
can be directly obtained from convolved feature at time t, and the encoder forward step in Algorithm 1
can be get rid of from the for loops?duration
annotation and should shift according to this annotation?beats
is fixed, but different music BPM is dynamic. According to BPM, the duration of the same CAU may be different. Is there any interpolation used within a CAU to adapt to BPM?Thanks @abcyzj , I have question about the training loss equation(3)
in your paper.
After Algorithm 1
, I got the predicted CAU sequence Y_gen
. I think the t
in equation(3)
is in beat scale, is the nll_loss
is computed on each beat or just the first beat in each predicted CAU?
Also, I found the model only repeatly predict [NIL]
(maybe there are too many [NIL]
padded at the front of CAU sequences). How do you handle this case?
BTW, I have no idea when performing inverse kinematics to caculate the rotation of human body pose. Could you give some libraries or methods to get the rotation of human body joints from Euclidean coordinates of these joints in your c3d data. Tks!
Thanks @abcyzj , I have question about the training loss
equation(3)
in your paper. AfterAlgorithm 1
, I got the predicted CAU sequenceY_gen
. I think thet
inequation(3)
is in beat scale, is thenll_loss
is computed on each beat or just the first beat in each predicted CAU? Also, I found the model only repeatly predict[NIL]
(maybe there are too many[NIL]
padded at the front of CAU sequences). How do you handle this case? BTW, I have no idea when performing inverse kinematics to caculate the rotation of human body pose. Could you give some libraries or methods to get the rotation of human body joints from Euclidean coordinates of these joints in your c3d data. Tks!
you reproducting the paper now? I have some questions now, can we talk about it?
Hi, @abcyzj , I have some problem about the choreography files: