ABSTRACT
Facial attractiveness is an ever-lasting issue in art and social science. It also draws considerable attention from multimedia community recently. In this paper, we develop a framework highlighting attractiveness-aware feature extracted from a pair of auto-encoders to learn human-like assessment of facial beauty. Our work is fully-automatic that does not require any landmark and puts no restrictions on the faces' pose, expressions, and lighting conditions and therefore is applicable on a larger and more diverse dataset. To this end, first, a pair of auto-encoders is built respectively with beauty images and non-beauty images, which can be used to extract attractiveness-aware features by putting test images into both encoders. Second, we further enhance the performance using an efficient robust low-rank fusion framework to integrate the predicted confidence scores which are obtained based on certain kinds of features. We show that our attractiveness-aware model with multiple layers of auto-encoders produces appealing results and performs better than previous appearance-based approaches.
- P. Aarabi, D. Hughes, K. Mohajer, and M. Emami. The automatic measurement of facial beauty. In IEEE International Conference on Systems, Man, and Cybernetics, volume 4, pages 2644--2647. IEEE, 2001.Google ScholarCross Ref
- T. R. Alley and M. R. Cunningham. Averaged faces are attractive, but very attractive faces are not average. 1991.Google Scholar
- B. C. Davis and S. Lazebnik. Analysis of human attractiveness using manifold kernel regression. In ICIP, pages 109--112. IEEE, 2008.Google ScholarCross Ref
- L. G. Farkas and J. C. Kolar. Anthropometrics and art in the aesthetics of women's faces. Clinics in Plastic Surgery, 14(4):599--616, 1987.Google ScholarCross Ref
- K. Grammer and R. Thornhill. Human facial attractiveness and sexual selection: The role of symmetry and averageness. Journal of Comparative Psychology, 108(3):233, 1994.Google ScholarCross Ref
- D. Gray, K. Yu, W. Xu, and Y. Gong. Predicting facial beauty without landmarks. In ECCV, pages 434--447. Springer, 2010. Google ScholarDigital Library
- Y. Jefferson. Facial beauty-establishing a universal standard. International Journal of Orthodontics-Milwaukee-, 15(1):9--26, 2004.Google Scholar
- G. Liu, Z. Lin, S. Yan, J. Sun, Y. Yu, and Y. Ma. Robust recovery of subspace structures by low-rank representation. TPAMI, 35(1):171--184, 2013. Google ScholarDigital Library
- Y. Mu. Computational facial attractiveness prediction by aesthetics-aware features. Neurocomputing, 99:59--64, 2013. Google ScholarDigital Library
- J. Nocedal. Updating quasi-newton matrices with limited storage. Mathematics of Computation, 35(151):773--782, 1980.Google ScholarCross Ref
- G. Rhodes. The evolutionary psychology of facial beauty. Annu. Rev. Psychol., 57:199--226, 2006.Google ScholarCross Ref
- D. Sutic, I. Breskovic, R. Huic, and I. Jukic. Automatic evaluation of facial attractiveness. In International Convention on Information and Communication Technology, Electronics and Microelectronics, pages 1339--1342. IEEE, 2010.Google Scholar
- R. White, A. Eden, and M. Maire. Automatic prediction of human attractiveness. UC Berkeley CS280A Project, 1:2, 2004.Google Scholar
- J. Whitehill and J. R. Movellan. Personalized facial attractiveness prediction. In IEEE International Conference on Automatic Face and Gesture Recognition, pages 1--7. IEEE, 2008.Google ScholarCross Ref
- H. Yan. Cost-sensitive ordinal regression for fully automatic facial beauty assessment. Neurocomputing, 129(0):334 -- 342, 2014. Google ScholarDigital Library
- G. Ye, D. Liu, I.-H. Jhuo, and S.-F. Chang. Robust late fusion with rank minimization. In CVPR, pages 3021--3028. IEEE, 2012. Google ScholarDigital Library
Index Terms
- Attractive or Not?: Beauty Prediction with Attractiveness-Aware Encoders and Robust Late Fusion
Recommendations
Age invariant face recognition and retrieval by coupled auto-encoder networks
Recently many promising results have been shown on face recognition related problems. However, age-invariant face recognition and retrieval remains a challenge. Inspired by the observation that age variation is a nonlinear but smooth transform and the ...
Face liveness detection using convolutional-features fusion of real and deep network generated face images
Highlights- A frame work for evaluating real-world and DNG images for face liveness detection.
AbstractConventionally, classifiers designed for face liveness detection are trained on real-world images, where real-face images and corresponding face presentation attacks (PA) are very much overlapped. However, a little research has been ...
Deep Face Swapping via Cross-Identity Adversarial Training
MultiMedia ModelingAbstractGenerative Adversarial Networks (GANs) have shown promising improvements in face synthesis and image manipulation. However, it remains difficult to swap the faces in videos with a specific target. The most well-known face swapping method, ...
Comments