High level describable attributes for predicting aesthetics and interestingness
Inhaltsverzeichnis
Referenz
Dhar, S., Ordonez, V., Berg, T.L.: High level describable attributes for predicting aesthetics and interestingness. In: Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, IEEE (2011) 1657-1664
DOI
http://dx.doi.org/10.1109/CVPR.2011.5995467
Abstract
With the rise in popularity of digital cameras, the amount of visual data available on the web is growing exponentially. Some of these pictures are extremely beautiful and aesthetically pleasing, but the vast majority are uninteresting or of low quality. This paper demonstrates a simple, yet powerful method to automatically select high aesthetic quality images from large image collections. Our aesthetic quality estimation method explicitly predicts some of the possible image cues that a human might use to evaluate an image and then uses them in a discriminative approach. These cues or high level describable image attributes fall into three broad types: 1) compositional attributes related to image layout or configuration, 2) content attributes related to the objects or scene types depicted, and 3) sky-illumination attributes related to the natural lighting conditions. We demonstrate that an aesthetics classifier trained on these describable attributes can provide a significant improvement over baseline methods for predicting human quality judgments. We also demonstrate our method for predicting the “interestingness” of Flickr photos, and introduce a novel problem of estimating query specific “interestingness”.
Extended Abstract
Bibtex
@INPROCEEDINGS{5995467,
author={S. Dhar and V. Ordonez and T. L. Berg},
booktitle={Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on},
title={High level describable attributes for predicting aesthetics and interestingness},
year={2011},
pages={1657-1664},
keywords={Internet;cameras;image processing;philosophical aspects;query processing;Flickr photo;aesthetic quality estimation;aesthetics prediction;baseline method;digital camera;high level describable attribute;human quality judgment;image collection;natural lighting condition;query estimation;sky-illumination attribute;visual data;Animals;Humans;Image color analysis;Lighting;Support vector machines;Training;Visualization},
doi={10.1109/CVPR.2011.5995467},
url={http://dx.doi.org/10.1109/CVPR.2011.5995467 http://de.evo-art.org/index.php?title=High_level_describable_attributes_for_predicting_aesthetics_and_interestingness},
ISSN={1063-6919},
month={June},
}
Used References
O. Axelsson. Towards a psychology of photography: dimensions underlying aesthetic appeal of photographs. In Perceptual and Motor Skills, 2007. 1659 http://dx.doi.org/10.2466/PMS.105.6.411-434
T. L. Berg and D. A. Forsyth. Animals on the web. In CVPR, 2006. 1661 http://dx.doi.org/10.1109/CVPR.2006.57
R. Datta, D. Joshi, J. Li, and J. Z. Wang. Studying aesthetics in photographic images using a computational approach. In ECCV, 2006. 1658, 1660
R. Datta, J. Li, and J. Z. Wang. Algorithmic inferencing of aesthetics and emotion in natural images: An exposition. In ICIP, 2008. 1658 http://dx.doi.org/10.1109/ICIP.2008.4711702
A. Farhadi, I. Endres, D. Hoiem, and D. A. Forsyth. Describing objects by their attributes. In CVPR, 2009. 1658 http://dx.doi.org/10.1109/CVPR.2009.5206772
L. Fei-Fei and P. Perona. A bayesian hierarchical model for learning natural scene categories. In CVPR, 2005. 1661 http://dx.doi.org/10.1109/CVPR.2005.16
V. Ferrari and A. Zisserman. Learning visual attributes. NIPS, 2007. 1658
J. Gardner, C. Nothelfer, and S. Palmer. Exploring aesthetic principles of spatial composition through stock photography. In VSS, 2008. 1659 http://dx.doi.org/10.1167/8.6.337
D. Hoiem, A. A. Efros, and M. Hebert. Geometric context from a single image. In ICCV, pages 654-661, 2005. 1661 http://dx.doi.org/10.1109/ICCV.2005.107
L. Itti and C. Koch. Computational modelling of visual attention. Nature Reviews Neuroscience, 2(3):194-203, Mar. 2001. 1659 http://dx.doi.org/10.1038/35058500
Y. Ke, X. Tang, and F. Jing. The design of high-level features for photo quality assessment. In CVPR, 2006. 1658, 1661, 1662 http://dx.doi.org/10.1109/CVPR.2006.303
N. Kumar, A. Berg, P. Belhumeur, and S. Nayar. Attribute and simile classifiers for face verification. In ICCV, 2009. 1657, 1658 http://dx.doi.org/10.1109/ICCV.2009.5459250
C. Lampert, H. Nickisch, and S. Harmeling. Learning to detect unseen object classes by between-class attribute transfer. In CVPR, 2009. 1658 http://dx.doi.org/10.1109/CVPR.2009.5206594
S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching. In CVPR, June 2006. 1660 http://dx.doi.org/10.1109/CVPR.2006.68
D. G. Lowe. Distinctive image features from scale invariant keypoints. IJCV, 2004. 1660 http://dx.doi.org/10.1023/B:VISI.0000029664.99615.94
T. Lui, J. Sun, N.-K. Zheng, X. Tang, and H.-Y. Shum. Learning to detect a salient object. In CVPR, 2007. 1659 http://dx.doi.org/10.1109/CVPR.2007.383047
Y. Luo and X. Tang. Photo and video quality evaluation: Focusing on the subject. In ECCV, 2008. 1658
C. Nothelfer, K. B. Schloss, and S. E. Palmer. The role of spatial composition in preference for color pairs. In VSS, 2009. 1659, 1660 http://dx.doi.org/10.1167/9.8.342
A. Oliva and A. Torralba. Modeling the shape of the scene: a holistic representation of the spatial envelope. IJCV, 2001. 1661
S. Palmer, E. Rosch, and P. Chase. Canonical perspective and the perception of objects. In Attention and Performance, 1981. 1658
F. Porikli. Integral histogram: A fast way to extract histograms in cartesian spaces. In CVPR, 2005. 1659 http://dx.doi.org/10.1109/CVPR.2005.188
K. B. Schloss and S. E. Palmer. Color preferences. In VSS, 2007. 1659, 1660
X. Sun, H. Yao, R. Ji, and S. Liu. Photo assessment based on computational visual attention model. In ACM MM, 2009. 1658 http://dx.doi.org/10.1145/1631272.1631351
H. Tong, M. Li, H. Zhang, J. He, and C. Zhang. Classification of digital photos taken by photographers or home users. In PCM, 2004. 1658
H. Tong, M. Li, H. Zhang, C. Zhang, J. He, and W.-Y. Ma. Learning no-reference quality metric by examples. In ICMM, 2005. 1658 http://dx.doi.org/10.1109/MMMC.2005.52
P. Viola and M. Jones. Robust real-time object detection. In IJCV, 2001. 1660
Links
Full Text
http://m.tamaraberg.com/papers/aesthetics_cvpr11.pdf
