Unsupervised Motion Representation Learning with Capsule Autoencoders

10/01/2021
by   Ziwei Xu, et al.
0

We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a spatio-temporal motion signal is divided into short, local, and semantic-agnostic snippets. In the higher level, the snippets are aggregated to form full-length semantic-aware segments. For both levels, we represent motion with a set of learned transformation invariant templates and the corresponding geometric transformations by using capsule autoencoders of a novel design. This leads to a robust and efficient encoding of viewpoint changes. MCAE is evaluated on a novel Trajectory20 motion dataset and various real-world skeleton-based human action datasets. Notably, it achieves better results than baselines on Trajectory20 with considerably fewer parameters and state-of-the-art performance on the unsupervised skeleton-based action recognition task.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/30/2023

Action Capsules: Human Skeleton Action Recognition

Due to the compact and rich high-level representations offered, skeleton...
research
08/31/2022

ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting

Current self-supervised approaches for skeleton action representation le...
research
03/20/2023

Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition

The self-supervised pretraining paradigm has achieved great success in s...
research
10/26/2017

Dynamic Routing Between Capsules

A capsule is a group of neurons whose activity vector represents the ins...
research
08/14/2023

Masked Motion Predictors are Strong 3D Action Representation Learners

In 3D human action recognition, limited supervised data makes it challen...
research
11/14/2020

Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition

In this paper, we focus on unsupervised representation learning for skel...

Please sign up or login with your details

Forgot password? Click here to reset