Cargando…
Spatio-temporal categorization for first-person-view videos using a convolutional variational autoencoder and Gaussian processes
In this study, HcVGH, a method that learns spatio-temporal categories by segmenting first-person-view (FPV) videos captured by mobile robots, is proposed. Humans perceive continuous high-dimensional information by dividing and categorizing it into significant segments. This unsupervised segmentation...
Autores principales: | Nagano, Masatoshi, Nakamura, Tomoaki, Nagai, Takayuki, Mochihashi, Daichi, Kobayashi, Ichiro |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9562109/ https://www.ncbi.nlm.nih.gov/pubmed/36246490 http://dx.doi.org/10.3389/frobt.2022.903450 |
Ejemplares similares
-
HVGH: Unsupervised Segmentation for High-Dimensional Time Series Using Deep Neural Compression and Statistical Generative Model
por: Nagano, Masatoshi, et al.
Publicado: (2019) -
Editorial: Language and Robotics
por: Taniguchi, Tadahiro, et al.
Publicado: (2021) -
Symbol Emergence as an Interpersonal Multimodal Categorization
por: Hagiwara, Yoshinobu, et al.
Publicado: (2019) -
Novelty detection in rover-based planetary surface images using autoencoders
por: Stefanuk, Braden, et al.
Publicado: (2022) -
Segmenting Continuous Motions with Hidden Semi-markov Models and Gaussian Processes
por: Nakamura, Tomoaki, et al.
Publicado: (2017)