Separating Style and Content with Bilinear Models

  title={Separating Style and Content with Bilinear Models},
  author={Joshua B. Tenenbaum and William T. Freeman},
  journal={Neural Computation},
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 familiar face or object seen under unfamiliar viewing conditions. Yet a general and tractable computational model of this ability to untangle the underlying factors of perceptual observations remains elusive (Hofstadter, 1985). Existing factor models (Mardia, Kent, & Bibby, 1979; Hinton & Zemel, 1994… CONTINUE READING
Highly Influential
This paper has highly influenced 98 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 845 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 1 time. VIEW TWEETS


Publications citing this paper.
Showing 1-10 of 474 extracted citations

A Study of Bilinear Models in Voice Conversion

J. Signal and Information Processing • 2011
View 15 Excerpts
Highly Influenced

Images, Frames, and Connectionist Hierarchies

Neural Computation • 2006
View 12 Excerpts
Highly Influenced

Bilinear Sparse Coding for Invariant Vision

Neural Computation • 2005
View 5 Excerpts
Highly Influenced

Learning typographic style: from discrimination to synthesis

Machine Vision and Applications • 2017
View 5 Excerpts
Highly Influenced

Unified subspace learning for incomplete and unlabeled multi-view data

Pattern Recognition • 2017
View 14 Excerpts
Highly Influenced

Cross-modal subspace learning for sketch-based image retrieval: A comparative study

Peng Xu, Ke Li, +3 authors Jun Guo
2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) • 2016
View 11 Excerpts
Highly Influenced

846 Citations

Citations per Year
Semantic Scholar estimates that this publication has 846 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 60 references

Computation and the single neuron

Nature • 1997
View 4 Excerpts
Highly Influenced

Fluid Concepts and Creative Analogies: A Review

AI Magazine • 1995
View 6 Excerpts
Highly Influenced

Matrix differential calculus with applications in statistics and econometrics

J. R. Magnus, H. Neudecker
View 4 Excerpts
Highly Influenced

Discriminant adaptive nearest neighbor classi cation

T. Hastie, R. Tibshirani
IEEE Pattern Analysis and Machine Intelligence • 1996
View 1 Excerpt
Highly Influenced

Dynamic error propagation networks

A. Robinson
Unpublished doctoral dissertation, Cambridge University. • 1989
View 2 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…