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.
- L. Bourdev, S. Maji, and J. Malik. Describing people: A poselet-based approach to attribute classification. In ICCV, 2011. Google ScholarDigital Library
- G. Carneiro, N. Silva, A. Bue, and J. Costeira. Artistic image classification: An analysis on the printart database. In ECCV, 2012. Google ScholarDigital Library
- M. Cimpoi, S. Maji, and A. Vedaldi. Deep filter banks for texture recognition and segmentation. In CVPR, 2015.Google ScholarCross Ref
- P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part-based models. PAMI, 32(9):1627--1645, 2010. Google ScholarDigital Library
- Y. Gong, L. Wang, R. Guo, and S. Lazebnik. Multi-scale orderless pooling of deep convolutional activation features. In ECCV, 2014.Google ScholarCross Ref
- F. S. Khan, S. Beigpour, J. van de Weijer, and M. Felsberg. Painting-91: a large scale database for computational painting categorization. MVA, 25(6):1385--1397, 2014. Google ScholarDigital Library
- F. S. Khan, J. Xu, J. van de Weijer, A. Bagdanov, R. M. Anwer, and A. Lopez. Recognizing actions through action-specific person detection. TIP, 24(11):4422--4432, 2015.Google ScholarDigital Library
- T. Mensink and J. Gemert. The rijksmuseum challenge: Museum-centered visual recognition. In ICMR, 2014. Google ScholarDigital Library
- M. Pandey and S. Lazebnik. Scene recognition and weakly supervised object localization with deformable part-based models. In ICCV, 2011. Google ScholarDigital Library
- K.-C. Peng and T. Chen. Cross-layer features in convolutional neural networks for generic classification tasks. In ICIP, 2015.Google ScholarDigital Library
- K.-C. Peng and T. Chen. A framework of extracting multi-scale features using multiple convolutional neural networks. In ICME, 2015.Google ScholarCross Ref
- A. Quattoni and A. Torralba. Recognizing indoor scenes. In CVPR, 2009.Google ScholarCross Ref
- J. Sanchez, F. Perronnin, T. Mensink, and J. Verbeek. Image classification with the fisher vector: Theory and practice. IJCV, 105(3):222--245, 2013. Google ScholarDigital Library
- K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.Google Scholar
- N. Zhang, R. Farrell, F. Iandola, and T. Darrell. Deformable part descriptors for fine-grained recognition and attribute prediction. In ICCV, 2013. Google ScholarDigital Library
Index Terms
- Combining Holistic and Part-based Deep Representations for Computational Painting Categorization
Recommendations
Multi-camera Based Human Tracking with Non-overlapping Fields of View
ICIG '09: Proceedings of the 2009 Fifth International Conference on Image and GraphicsThis paper presents approach for an automated surveillance system which performs human detection and tracking across multiple non-overlapping cameras. Emphasis is put at single camera level where motion based segmentation is achieved using optical flow ...
Multitask painting categorization by deep multibranch neural network
Highlights- A novel deep multibranch multitask neural network architecture.
- The different ...
AbstractWe propose a novel deep multibranch and multitask neural network for artist, style, and genre painting categorization. The multibranch approach allows us to exploit at the same time the coarse layout of the painting and the fine-...
Comments