Separating Style and Content with Bilinear Models
Top Cited Papers
- 1 June 2000
- journal article
- Published by MIT Press in Neural Computation
- Vol. 12 (6), 1247-1283
- https://doi.org/10.1162/089976600300015349
Abstract
Perceptual systems routinely separate “content” from “style,” classifying familiar words spoken in an unfamiliar accent, identifying a font or handwriting style across letters, or recognizing a fam...Keywords
This publication has 24 references indexed in Scilit:
- Generative models for discovering sparse distributed representationsPhilosophical Transactions Of The Royal Society B-Biological Sciences, 1997
- Statistical Approach to Shape from Shading: Reconstruction of Three-Dimensional Face Surfaces from Single Two-Dimensional ImagesNeural Computation, 1996
- Image Representations for Visual LearningScience, 1996
- Discriminant adaptive nearest neighbor classificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- The Helmholtz MachineNeural Computation, 1995
- The "Wake-Sleep" Algorithm for Unsupervised Neural NetworksScience, 1995
- Connectionist generalization for production: An example from GridFontNeural Networks, 1992
- Color constancy: surface color from changing illuminationJournal of the Optical Society of America A, 1992
- Encoding of Spatial Location by Posterior Parietal NeuronsScience, 1985