Unsupervised Motion Representation Learning with Capsule Autoencoders

Dec-23-2025, 20:03:19 GMT–Neural Information Processing Systems

We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance.

artificial intelligence, machine learning, proceedings, (4 more...)

Neural Information Processing Systems

Dec-23-2025, 20:03:19 GMT

Conferences Web Page

Add feedback

Technology:
- Information Technology > Artificial Intelligence > Machine Learning (0.86)