The Menpo Facial Landmark Localisation in-the-Wild Challenge & Workshop to be held in conjunction with International Conference on Computer Vision & Pattern Recognition (CVPR) 2017, Hawaii, USA.
Stefanos Zafeiriou, Imperial College London, UK firstname.lastname@example.org
Maja Pantic, Imperial College London, UK email@example.com
Grigorios Chrysos, Imperial College London, UK firstname.lastname@example.org
George Trigeorgis Imperial College London, UK email@example.com
Jiakang Deng Imperial College London, UK firstname.lastname@example.org
Jie Shen Imperial College London, UK email@example.com
Currently comprehensive benchmarks exist for facial landmark localization and tracking (see 300W  and 300VW  challenges). Nevertheless, these benchmarks are mainly about (near) frontal faces. In CVPR 2017, we make a significant step further and present a new comprehensive multi-pose benchmark, as well as organize a workshop-challenge for landmark detection in images displaying arbitrary poses. To this end we have annotated a large set of profile faces with 39 fiducial points. Furthermore, we have annotated many new images of (near) frontal faces using the standard 68 point markup. The challenge will represent the very first thorough quantitative evaluation on multipose face landmark detection. Furthermore, the competition will explore how far we are from attaining satisfactory facial landmark localisation in arbitrary poses. The results of the Challenge will be presented at the Faces " in-the-wild" (Wild-Face) Workshop to be held in conjunction with CVPR 2017.
In order to develop a comprehensive benchmark for evaluating facial landmark localisation
algorithms in the wild in arbitrary poses, we have annotated both (near) frontal, as well as profile faces
in the wild. To this end, we annotated (a) many new in-the-wild (near) frontal images
with regards to the same mark-up (i.e. set of facial landmarks) used in the 300 W competition
[1,2] (a total of 68 landmarks, please see Fig. 1) and (b) many in-the-wild profile facial images using a 39 landmakrs mark-up, please see Fig. 2
The training facial samples and annotations are available to download from here. Participants will be able to train their facial landmark tracking algorithms using the above training set and the data from 300W competition.
The training data contain tha facial images and their corresponding annotation (.pts file).
Participants will have their algorithms tested on other facial in-the-wild images which will be provided in a predefined date (see below). This dataset aims at testing the ability of current systems for fitting unseen subjects, independently of variations in pose, expression, illumination, background, occlusion, and image quality.
A winner for each category (profile and (near) frontal) will be announced. Participants do not need to submit the executable to the organisers but only the results on the test images. The participants can take part in one or more of the aforementioned, (near) frontal or profile challenges. The Menpo Challenge organisers will not take part in the competition. The test set images are similar in nature to those of Menpo training set.
Fitting performance will be assessed on the same mark-up provided for the training using well-known error
measures. In particular, the average Euclidean point-to-point error normalized distance will be used [1,2] (normalised appropriately for profile and frontal images). Matlab code for calculating the error can be downloaded here. The error will be calculated over (a) all landmarks, and (b) the facial feature landmarks (eyebrows, eyes, nose, and mouth). The cumulative curve corresponding to the percentage of test images for which the error was less than a specific value will be produced. Finally, these results will then be returned to the participants for inclusion in their papers. Benchmark results of a standard approach of generic face detection plus generic facial landmark detection will be used (e.g., Viola Jones plus Active Appearance Models ).
The authors acknowledge that if they decide to submit, the resulting curve might be used by the organisers in any related visualisations/results. The authors are prohibited from sharing the results with other contesting teams.
The organisers cannot publish the resulting pts of the participants without their consent. Only one final submission per team will be accepted for each team to avoid overfitting the testset. This also means that the participants should use their own validation set, should they wish to test their algorithms and not try to submit multiple times. Each image contains a single face annotated and it is the one that is closer to the centre of the image.
Our aim is to accept up to 10 papers to be orally presented at the workshop.
Challenge participants should submit a paper to the 300-VW Workshop, which summarizes the methodology and the achieved performance of their algorithm. Submissions should adhere to the main CVPR 2017 proceedings style. The workshop papers will be published in the CVPR 2017 proceedings. Please sign up in the submissions system to submit your paper.
Workshop Administrator: firstname.lastname@example.org
 C. Sagonas, G. Tzimiropoulos, S. Zafeiriou, & M. Pantic, (2013, December). 300 faces in-the-wild
challenge: The first facial landmark localization challenge. In Computer Vision Workshops (ICCVW), 2013
IEEE International Conference on (pp. 397-403).
 Shen, J., Zafeiriou, S., Chrysos, G. G., Kossaifi, J., Tzimiropoulos, G., & Pantic, M. (2015, December). The first facial landmark tracking in-the-wild challenge: Benchmark and results. In Computer Vision Workshop (ICCVW), 2015 IEEE International Conference on (pp. 1003-1011). IEEE.
 G. Tzimiropoulos., J. Alabort., S. Zafeiriou., and M. Pantic, “Generic active appearance models revisited,”
 R. Gross, I. Matthews, J. Cohn, T. Kanade, S. Baker. “Multi-pie,” IVC, 28(5):807–813, 2010
The Faces "in-the-wild" Challenge & Workshop has been supported by H2020 Tesla project and the EPSRC projects FACE2VM and ADAManT.