Fetching the paper…

Reading the bibliography…

2018

The Shape of Art History in the Eyes of the Machine

Elgammal, Ahmed, Mazzone, Marian, Liu, Bingchen et al.

Original
PDF
Post on X

Understand

How does the machine classify styles in art? And how does it relate to art historians' methods for analyzing style? Several studies have shown the ability of the machine to learn and predict style categories, such as Renaissance, Baroque, Impressionism, etc., from images of paintings.

This implies that the machine can learn an internal representation encoding discriminative features through its visual analysis.
However, such a representation is not necessarily interpretable.
We conducted a comprehensive study of several of the state-of-the-art convolutional neural networks applied to the task of style classification on 77K images of paintings, and analyzed the learned representation through correlation analysis with concepts derived from art history.

The Shape of Art History in the Eyes of the Machine · Around

Built on

H. Wölfflin, Principles of Art History: The Problem of the Development of Style in Later Art
1950
Earlier work this paper cites.
M. Schapiro, Style
1953
Earlier work this paper cites.
E. Gombrich, Style
1968
Earlier work this paper cites.
A. Hyvärinen, Fast and robust fixed-point algorithms for independent component analysis
1999
Earlier work this paper cites.
S. T. Roweis, L. K. Saul, Nonlinear dimensionality reduction by locally linear embedding
2000
Earlier work this paper cites.
A. Hyvarinen, J. Karhunen, E. Oja, Independent Component Analysis
2001
Earlier work this paper cites.

Similar

I. Jolliffe, Principle component analysis
2002
Cited alongside, same era.
L. Shamir et al, Impressionism, Expres-sionism, Surrealism: Automated Recognition of Painters and Schools of Art
2010
Cited alongside, same era.
A. Krizhevsky, I. Sutskever, G. E. Hinton, Imagenet classification with deep convolutional neural networks
2012
Cited alongside, same era.
S. Karayev, et al, Recognizing image style
Original
2013
Cited alongside, same era.
K. Simonyan, A. Zisserman. Very deep convolutional networks for large-scale image recognition
Original
2014
Cited alongside, same era.
L. Manovich, Data science and digital art history
2015

Then

Y. LeCun, Y. Bengio, G. Hinton, Deep learning
2015
Later among the works it cites.
O. Russakovsky, et al, ImageNet Large Scale Visual Recognition Challenge
2015
Later among the works it cites.
B. Saleh, K. Abe, R. S. Arora, A. Elgammal, Toward automated discovery of artistic influence
2016
Later among the works it cites.
B. Saleh, A. Elgammal, Large-scale classification of fine-art paintings: learning the right metric on the right features
2016
Later among the works it cites.
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition
2016
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.