Spatio-temporal categorization for first-person-view videos using a convolutional variational autoencoder and Gaussian processes.
Masatoshi NaganoTomoaki NakamuraTakayuki NagaiDaichi MochihashiIchiro KobayashiPublished in: Future Internet (2022)
Keyphrases
- gaussian processes
- spatio temporal
- gaussian process
- gaussian process regression
- human actions
- restricted boltzmann machine
- covariance function
- spatial and temporal
- gaussian process models
- human pose estimation
- video frames
- video sequences
- image sequences
- text categorization
- moving objects
- multi task
- deep learning
- active learning
- video data