Recognizing Image Style

@article{Karayev2013RecognizingIS,
  title={Recognizing Image Style},
  author={Sergey Karayev and Matthew Trentacoste and Helen Han and Aseem Agarwala and Trevor Darrell and Aaron Hertzmann and Holger Winnemoeller},
  journal={ArXiv},
  year={2013},
  volume={abs/1311.3715}
}
The style of an image plays a significant role in how it is viewed, but style has received little attention in computer vision research. We describe an approach to predicting style of images, and perform a thorough evaluation of different image features for these tasks. We find that features learned in a multi-layer network generally perform best -- even when trained with object class (not style) labels. Our large-scale learning methods results in the best published performance on an existing… 
[PDF] Semantic Reader
397 Citations
Highly Influential Citations
38
Background Citations
214
Methods Citations
137
Results Citations
15

397 Citations

An unsupervised approach for comparing styles of illustrations

An unsupervised approach to achieve accurate and efficient stylistic comparison among illustrations and experimental evaluation of the proposed method by using multiple benchmark datasets indicates that the proposedmethod outperforms existing approaches.

Image Representations for Style Retrieval, Recognition and Background Replacement Tasks

  • Computer Science
  • 2020
This work proposes a data-driven approach to sky-replacement that avoids color correction by finding a diverse set of skies that are consistent in color and natural illumination with the query image foreground and proposes an unsupervised protocol for learning a neural embedding of visual style of images.

Unsupervised Image Style Embeddings for Retrieval and Recognition Tasks

An unsupervised protocol for learning a neural embedding of visual style of images using a proxy measure for forming triplets of anchor, similar, and dissimilar images to learn a compact style embedding that is useful for style-based search and retrieval.

Blending texture features from multiple reference images for style transfer

An algorithm that learns a desired style of artwork from a collection of images and transfers this style to an arbitrary image using a feature space constructed from statistical properties of CNN feature responses, and is capable of synthesizing an appropriate texture that belongs to the desired style.

Recognizing Art Style Automatically with deep learning

The use of deep residual neural is investigated to solve the problem of detecting the artistic style of a painting and outperform existing approaches to reach an accuracy of 62% on the Wikipaintings dataset (for 25 different style).

Inferring Painting Style with Multi-Task Dictionary Learning

This paper presents a novel dictionary learning approach to automatically uncover the artistic style from paintings, by automatically decoupling style-specific and artist-specific patterns, and shows that this approach significantly outperforms state-of-the-art methods.

Recognizing Art Style Automatically in Painting with Deep Learning

The use of deep residual neural is investigated to solve the problem of detecting the artistic style of a painting and outperform existing approaches to reach an accuracy of 62 on the Wikipaintings dataset (for 25 different style).

CNN-based Style Vector for Style Image Retrieval

This paper proposed a style vector which are generated from a style matrix with PCA dimension reduction which outperformed the results by common CNN features and found PCA-compression boosted the performance.

Toward the Automatic Retrieval and Annotation of Outsider Art images: A Preliminary Statement

The preliminary experiments have provided motivation to think that, as is the case with traditional styles, Outsider Art can be computationally modelled with objective means by using training datasets and CNN models.

Style retrieval from natural images

This work proposes a ranking model for style identification based on random forests, and introduces dimension reduction and pruning techniques for the authors' random forests to handle the high dimensionality of visual features.
...

References

SHOWING 1-10 OF 25 REFERENCES

High level describable attributes for predicting aesthetics and interestingness

This paper demonstrates a simple, yet powerful method to automatically select high aesthetic quality images from large image collections and demonstrates that an aesthetics classifier trained on describable attributes can provide a significant improvement over baseline methods for predicting human quality judgments.

AVA: A large-scale database for aesthetic visual analysis

A new large-scale database for conducting Aesthetic Visual Analysis: AVA, which contains over 250,000 images along with a rich variety of meta-data including a large number of aesthetic scores for each image, semantic labels for over 60 categories as well as labels related to photographic style is introduced.

Learning beautiful (and ugly) attributes

This work proposes to discover and learn the visual appearance of attributes automatically, using the recently introduced AVA database which contains more than 250,000 images together with their user ratings and textual comments.

Aesthetic Visual Quality Assessment of Paintings

A group of methods to extract features to represent both the global characteristics and local characteristics of a painting are designed, which can classify high-quality and low-quality paintings with performance comparable to humans.

Dating Historical Color Images

The task of automatically estimating the age of historical color photographs is introduced and data-driven camera response function estimation is applied to historical color imagery, demonstrating its relevance to both the age estimation task and the popular application of imitating the appearance of vintage color photography.

The Rijksmuseum Challenge: Museum-Centered Visual Recognition

This paper offers four automatic visual recognition challenges consisting of predicting the artist, type, material and creation year, and includes a set of baseline results, and makes available state-of-the-art image features encoded with the Fisher vector.

What makes an image popular?

The importance of image cues, such as color, gradients, deep learning features and the set of objects present, as well as the importance of various social cues such as number of friends or number of photos uploaded that lead to high or low popularity of images are shown.

Meta-class features for large-scale object categorization on a budget

A novel image descriptor enabling accurate object categorization even with linear models and it is demonstrated that simple linear SVMs trained on the authors' meta-class descriptor significantly outperform the best known classifier on the Caltech256 benchmark.

The Interestingness of Images

This work introduces a set of features computationally capturing the three main aspects of visual interestingness and builds an interestingness predictor from them, shown on three datasets with varying context, reflecting the prior knowledge of the viewers.

What makes an image memorable?

It is shown that memorability is a stable property of an image that is shared across different viewers, and a database for which each picture will be remembered after a single view is introduced.