Human Age Estimation With Regression on Discriminative Aging Manifold

By Yun Fu, Thomas S. Huang. IEEE transactions on multimedia, 2008

462 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cdfe859fbe15e40847399dbad0f0c5a258ab7854

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

1. Luc Van Gool
2. Xiaogang Wang
3. Dacheng Tao
4. Chen Change Loy
5. Yu Qiao
6. Tao A. Xiang
7. Yi Yang
8. Ming-Hsuan Yang

Citations in the corpus

• Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval (2014, background): “Most existing age-related works for face image analysis focus on age estimation [14,15,40,25,34,7,38,6,10,22,21] and age simulation [16,30,28,29,24].”
• What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics (2016, unknown): “Fu and Huang (2008) [69] AMF (OLPP) YGA 800(M), 800(F) MAE = 8.”
• Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks (2016, unknown): “We refer to [42, 20, 14, 26, 2, 9] for broader literature reviews.”
• Age and Gender Estimation of Unfiltered Faces (2014, methodology): “The UIUC-IFP-Y Internal Aging [13], [14], extensively used by the SMILE lab at Northeastern University, is not publicly available due to intellectual property limitations, but presumably may be obtained by contacting its authors”
• Facial Age Estimation by Learning from Label Distributions (2010, methodology): “For example, Fu et al. [8], [10] proposed an age estimation method based on multiple linear regression on the discriminative aging manifold of face images.”
• Age and gender classification using convolutional neural networks (2015, unknown): “These methods therefore present experimental results only on constrained data-sets of near-frontal images (e.g UIUC-IFP-Y [12] [19] ,FG-NET [30] and MORPH [43]).”
• Human age estimation using bio-inspired features (2009, methodology): “The performance of age estimation is measured by the mean absolute error (MAE) and the cumulative score (CS) [ 7 , 12].”
• Learning ordinal discriminative features for age estimation (2012, methodology): “[9] learned a common aging pattern or trend for many individuals at each age via manifold learning.”
• Cumulative Attribute Space for Age and Crowd Density Estimation (2013, methodology): “To exploit this observation, most existing approaches to the problem consider a regression solution in which a mapping function is learned explicitly between high dimensional feature input vectors and scalar output values [4, 5, 8, 10, 12, 15, 16, 33, 35].”
• Ordinal hyperplanes ranker with cost sensitivities for age estimation (2011, methodology): “In our work, the absolute cost associated with the MAE serves as the cost sensitivity function: costkplq |l k|, for k 1, ...,K. (5) The CS performance measurement proposed by Geng et al. [10] is defined as CSpLq pMe L{Mq 100%, (6) where Me L is the number of test images with the absolute error e les”
• Demographic Estimation from Face Images: Human vs. Machine Performance (2015, background): “Since then, a significant progress has been made on automatic demographic estimation, and a number of approaches have been reported in the literature [8], [17], [19], [21], [23], [27], [29], [33], [39], [44], [51], [54].”
• Neighborhood repulsed metric learning for kinship verification (2012, unknown): “Representative examples include face recognition [5], [8], [10], [20], [22], [27], [28], [35], [37], [40], [41], [42], [43], [54], [55], [56], [58], [64], [65], [66], [67], [68], facial expression recognition [11], [18], [70], facial age estimation [19], [21], [24], [25], [31], [39], gender classifi”
• Ordinal Regression with Multiple Output CNN for Age Estimation (2016, methodology): “In previous methods, age estimation is often cast as a multi-class classification [12][15] or a metric regression problem [11][15][14].”
• Age Synthesis and Estimation via Faces: A Survey (2010, methodology): “The CS [16], [36] is defined as CS ð j Þ ¼ N e (cid:7) j =N (cid:4) 100% , where N e (cid:7) j is the number of test images on which the age estimation makes an absolute error no higher than j years.”
• Multi-task warped Gaussian process for personalized age estimation (2010, methodology): “Moreover, unlike methods which need to specify the form of the regression functions [18] or determine many parameters in the functions using inefficient methods such as cross validation [32, 5, 11], the form of the regression functions in MTWGP is implicitly defined by the kernel function and all th”