Multi-task warped Gaussian process for personalized age estimation

By Yu Zhang, Dit-Yan Yeung. 2010

210 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

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

In Evaluation & Benchmarks

Citations in the corpus

An Overview of Multi-task Learning (2018, background): “Specifically, applications of MTL based on facial images include face verification [84], personalized age estimation [85], multi-cue face recognition [86], head-pose estimation [22,87], facial landmark detection [18], and facial image rotation [88].”
A Survey on Multi-Task Learning (2017, background): “In [165], a multi-task warped Gaussian process is proposed for personalized age estimation, where each task corresponds to a person and different tasks share the kernel parameters and warped function but with different noise levels.”
Surpassing Human-Level Face Verification Performance on LFW with GaussianFace (2014, background): “However, most of them [60, 11, 6, 44, 25, 49, 61] have only considered the symmetric multi-task learning, which means that all tasks have been assumed to be of equal importance, whereas our purpose is to enhance performance on a target task given all other source tasks.”
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”
Feature-based transfer learning with real-world applications (2010, background): “Applications of transfer learning in these fields include image classification [202, 158, 185, 218, 161, 94, 177], image retrieval [73, 115, 38], face verification from images [196], age estimation from facial images [225], image semantic segmentation [190], video retrieval [208, 73], video concept ”
Cumulative Attribute Space for Age and Crowd Density Estimation (2013, methodology): “Settings – For FG-NET, we followed the same leave-oneperson-out setting as in [7, 15, 32, 33, 35].”
Learning ordinal discriminative features for age estimation (2012, methodology): “Given facial features, age estimation can be converted into a multiclass classification problem [11, 9] or a regression problem [14, 30, 28].”
Facial Age Estimation by Learning from Label Distributions (2010, methodology): “By using the Spatially Flexible Patch (SFP) as the feature descriptor, the age regression was further improved with the patch-based Gaussian mixture model [38] and the patch-based hidden Markov model [41].”
Flexible Clustered Multi-Task Learning by Learning Representative Tasks (2016, background): “The new approach allows an arbitrary task to be described by multiple representative tasks, effectively soft-assigning a task to multiple clusters with different weights.”
Local Rademacher Complexity-based Learning Guarantees for Multi-Task Learning (2016, background): “Some recent applications include computational genetics [63], image segmentation [1], HIV therapy screening [14], collaborative ﬁltering [18], age estimation from facial images [67], and sub-cellular location prediction [64], just to name a few prominent ones.”