The State of the Art: Object Retrieval in Paintings using Discriminative Regions
By Elliot J. Crowley, Andrew Zisserman. 2014
106 citations recorded by the source corpus.
The objective of this work is to recognize object categories (such as animals and vehicles) in paintings, whilst learning these categories from natural images. This is a challenging problem given the substantial differences between paintings and natural images, and variations in depiction of objects in paintings. We first demonstrate that classifiers trained on natural images of an object category have quite some success in retrieving paintings containing that category. We then draw upon recent work in mid-level discriminative patches to develop a novel method for reranking paintings based on their spatial consistency with natural images of an object category. This method combines both class based and instance based retrieval in a single framework. We quantitatively evaluate the method over a number of classes from the PASCAL VOC dataset, and demonstrate significant improvements in rankings of the retrieved paintings over a variety of object categories.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Peter Hall
- Qi Wu
- Hongping Cai
- Tadeo Corradi
- Anton van den Hengel
- Chunhua Shen
- Dacheng Tao
- Luc Van Gool
Citations in the corpus
- The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs (2015, methodology): “So far every method we have experimented that uses some kind of spatial information shows less fall away in the cross-depiction problem; this is true also of [12].”
- Understanding and Creating Art with AI: Review and Outlook (2021, unknown): “Art500k [92] 550k Artist, genre, style, event, historical figure retrieval OmniArt [127] 2M Artist, style, period, type, iconography, color classification/object detection ArtDL [101] 42k Iconographic classification PRINTART [16] 1k Object/pose retrieval Paintings [34] 8.”