HIGHLIGHTS
- who: Guowei Chen from the New Media Institute, Communication University of China, Chaoyang, Beijing, China have published the paper: 3D Human Pose Estimation Based on Transformer Algorithm, in the Journal: Mobile Information Systems of 29/08/2022
- what: The aim of using pooling layers is to obtain translation invariance, making the model focus on the presence of a feature rather than the location of the feature. On the one hand, most HPE research focuses on increasing accuracy, but it neglects the crucial balance between model speed and accuracy that is essential to HPE efficiency.
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.