Comments (2)
I'm glad to hear that our code has helped you.
- Why don't you use a four-dimensional vector 's_t' to control all four style attributes simultaneously
Doing this is entirely possible, and covered by the general method described in our paper. In fact, it is one of the reasons that we wrote s_t as a vector in our text and figures. The different things and control setups we considered in our experiments (such as the four specific style attributes) are mere examples of the general formulation we propose.
Our experiments in the StyleGestures paper did not study simultaneous control of the four different style attributes from the experiments for several reasons:
- There were constraints on the time available to us.
- We were already running out of space for content in the article, and were having to delete valuable parts of our article because it was too long to be accepted.
- Simultaneous control over multiple style aspects seemed more difficult to evaluate well and in a principled manner, since the value(s) of one attribute might affect the efficacy of control for another attribute. By limiting the evaluation to one-dimensional control, we could make clearer plots and visualisations like those in Fig. 4 of the paper.
- We think the article still is a strong article even without also including control over multiple style aspects in the experiments.
- Can I control a single style property with a multiple dimensional style input vector 's_t'?
Yes, you absolutely can. Such parametrisations are common practice in deep learning, for instance to represent different individual voices in a "speaker space" in text-to-speech. In fact, what you describe is another reason that we wrote s_t to in our paper to emphasise the vector nature of the control signal, and is again covered by the general formulation we propose.
I hope this answers your questions!
from stylegestures.
Thank you very much for explanation. I'm sorry for opening a duplicate of this issue by mistake.
from stylegestures.
Related Issues (20)
- Strange results when I train with multiple GPUs. HOT 2
- bvh files with fixed frames
- Difference between time_steps and seqlen? HOT 2
- Possible bug when computing the log-det of Jacobian for affine coupling HOT 2
- About datasets HOT 1
- For the freshmen about Gesture Generation HOT 2
- Questions about the latent random variable Z HOT 2
- The Python version
- About the Cuda version HOT 4
- About the swapaxes for self.x and self.cond HOT 6
- This dataset link doesn't seem to work. HOT 2
- The dataset are inconsistent HOT 10
- Excuse me, where can I find the dataset used by Example3 in readme? HOT 11
- This is the curve when I use two different data sets for training, and the parameters are the same. It can be roughly seen that the loss in Figure 1 will be lower than that in Figure 2, which can indicate that the performance of the first trained model will be better? HOT 6
- How to apply the output file(*.bvh) to 3D model file(*.3ds) HOT 3
- Some questions about the style control HOT 1
- About the dataset HOT 2
- The trained model posture shakes badly. What might be the cause? Is there any way to solve this problem? HOT 2
- Pre-trained models
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stylegestures.