Combining Holistic and Part-based Deep Representations for Computational Painting Categorization
Open Access
- 6 June 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 339-342
Abstract
Automatic analysis of visual art, such as paintings, is a challenging inter-disciplinary research problem. Conventional approaches only rely on global scene characteristics by encoding holistic information for computational painting categorization. We argue that such approaches are sub-optimal and that discriminative common visual structures provide complementary information for painting classification. We present an approach that encodes both the global scene layout and discriminative latent common structures for computational painting categorization. The region of interests are automatically extracted, without any manual part labeling, by training class-specific deformable part-based models. Both holistic and region-of-interests are then described using multi-scale dense convolutional features. These features are pooled separately using Fisher vector encoding and concatenated afterwards in a single image representation. Experiments are performed on a challenging dataset with 91 different painters and 13 diverse painting styles. Our approach outperforms the standard method, which only employs the global scene characteristics. Furthermore, our method achieves state-of-the-art results outperforming a recent multi-scale deep features based approach by $6.4\\%$ and $3.8\\%$ respectively on artist and style classification.
Keywords
This publication has 14 references indexed in Scilit:
- Cross-layer features in convolutional neural networks for generic classification tasks2015
- Recognizing Actions Through Action-Specific Person DetectionIEEE Transactions on Image Processing, 2015
- Deep filter banks for texture recognition and segmentation2015
- Painting-91: a large scale database for computational painting categorizationMachine Vision and Applications, 2014
- The Rijksmuseum Challenge2014
- Multi-scale Orderless Pooling of Deep Convolutional Activation Features2014
- Artistic Image Classification: An Analysis on the PRINTART Database2012
- Scene recognition and weakly supervised object localization with deformable part-based models2011
- Describing people: A poselet-based approach to attribute classification2011
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009