ChaLearn Looking at People and Faces of the World: Face AnalysisWorkshop and Challenge 2016

By Sergio Escalera, M. Torres, Brais Martínez, Xavier Baró, Hugo Jair Escalante, Isabelle M Guyon, Georgios Tzimiropoulos, Ciprian Adrian Corneanu, Marc Oliu, Mohammad Ali Bagheri and 1 more. 2016

107 citations recorded by the source corpus.

We present the 2016 ChaLearn Looking at People and Faces of the World Challenge and Workshop, which ran three competitions on the common theme of face analysis from still images. The first one, Looking at People, addressed age estimation, while the second and third competitions, Faces of the World, addressed accessory classification and smile and gender classification, respectively. We present two crowd-sourcing methodologies used to collect manual annotations. A custom-build application was used to collect and label data about the apparent age of people (as opposed to the real age). For the Faces of the World data, the citizen-science Zooniverse platform was used. This paper summarizes the three challenges and the data used, as well as the results achieved by the participants of the competitions. Details of the ChaLearn LAP FotW competitions can be found at http://gesture.chalearn.org.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, background): “FotW [13] Flickr 25K X X X yes”
Compacting, Picking and Growing for Unforgetting Continual Learning (2019, methodology): “For gender classification, we combine FotW [9] and IMDB-Wiki [37] datasets and classify faces into three categories, male, female and other.”
ChaLearn looking at people: A review of events and resources (2017, background): “Together with the challenges and their associated work-shops, we organized a series of Special Issues and Special Topics related to LAP in prestigious journals.”
InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity (2017, methodology): “InclusiveFaceNet matches or improves over a baseline without transfer learning, deﬁning a new state-of-the-art performance for face attribute detection across gender boundaries in both the CelebA (Liu et al., 2015) and FotW (Escalera et al., 2016) datasets.”
FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation (2021, background): “To date, numerous large scale face image datasets [21, 31, 13, 70, 37, 23, 43, 69, 14, 26, 48, 8, 40] have been proposed and fostered research and development for automated face detection [35, 20], alignment [67, 46], recognition [57, 51], generation [68, 5, 25, 58], modification [3, 32, 18], and at”
Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning (2019, methodology): “We also compare the accuracy of our PAENet with the state of the art and baseline approaches in expression and gender classification, such as AffectNet [16], CAKE [7] and SIATMMLAB [4].”
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach (2017, methodology): “With PCA appearance features and keypoint features, Multi-task Restricted Boltzmann Machine (RBM) was adopted in [32] for estimating 40 face attributes on the CelebA database, and gender and smile classifications on the FotW database [44].”
Mitigating Bias in Gender, Age and Ethnicity Classification: A Multi-task Convolution Neural Network Approach (2018, methodology): “[24] collected the Faces of the World (FotW) dataset, with the aim to achieve a uniform distribution across two genders and four ethnic groups.”