Y-Autoencoders: Disentangling latent representations via sequential encoding
Authors:
- Massimiliano PatacchiolaMPMassimiliano Patacchiola
- Patrick Fox-RobertsPFPatrick Fox-Roberts
- Edward RostenEREdward Rosten
- 1 December 2020
- journal article
- research article
- Published by Elsevier in Pattern Recognition Letters
- Vol. 140, 59-65
Abstract
No abstract availableKeywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Multimodal Face-Pose Estimation With Multitask Manifold Deep LearningIEEE Transactions on Industrial Informatics, 2018
- Pose transforming network: Learning to disentangle human posture in variational auto-encoded latent spacePattern Recognition Letters, 2018
- Deep generative video predictionPattern Recognition Letters, 2018
- Back projection: An effective postprocessing method for GAN-based face sketch synthesisPattern Recognition Letters, 2018
- Head pose estimation in the wild using Convolutional Neural Networks and adaptive gradient methodsPattern Recognition, 2017
- Multimodal Deep Autoencoder for Human Pose RecoveryIEEE Transactions on Image Processing, 2015
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Neural networks and principal component analysis: Learning from examples without local minimaNeural Networks, 1989