HVGH: Unsupervised Segmentation for High-Dimensional Time Series Using Deep Neural Compression and Statistical Generative Model
Humans perceive continuous high-dimensional information by dividing it into meaningful segments, such as words and units of motion. We believe that such unsupervised segmentation is also important for robots to learn topics such as language and motion. To this end, we previously proposed a hierarchi...
Main Authors: | Masatoshi Nagano, Tomoaki Nakamura, Takayuki Nagai, Daichi Mochihashi, Ichiro Kobayashi, Wataru Takano |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2019-11-01
|
Series: | Frontiers in Robotics and AI |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/frobt.2019.00115/full |
Similar Items
-
Segmenting Continuous Motions with Hidden Semi-markov Models and Gaussian Processes
by: Tomoaki Nakamura, et al.
Published: (2017-12-01) -
Dance Movement Learning for Labanotation Generation Based on Motion-Captured Data
by: Min Li, et al.
Published: (2019-01-01) -
Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses
by: Songle Chen, et al.
Published: (2020-09-01) -
A Solution for Improving Data Capture Process Aimed at Collecting Azeri Dance Data: An Action Research
by: Afsaneh Yadaei, et al.
Published: (2020-02-01) -
A Perceptual-Based Noise-Agnostic 3D Skeleton Motion Data Refinement Network
by: Shu-Jie Li, et al.
Published: (2020-01-01)