Disentangling Multiple Features in Video Sequences Using Gaussian Processes in Variational Autoencoders.
Sarthak BhagatShagun UppalZhuyun YinNengli LimPublished in: ECCV (23) (2020)
Keyphrases
- gaussian processes
- multiple features
- video sequences
- gaussian process
- data fusion
- denoising
- image segmentation
- metric learning
- multi task
- incremental learning
- feature space
- visual information
- feature vectors
- low level features
- feature set
- video data
- relevance feedback
- hyperparameters
- video frames
- image retrieval
- image sequences
- combining multiple
- multiple views
- learning tasks
- class labels
- multi view
- dimensionality reduction
- three dimensional
- machine learning