The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results

Detection and tracking of faces in image sequences is among the most well studied problems in the intersection of statistical machine learning and computer vision. Often, tracking and detection methodologies use a rigid representation to describe the facial region 1, hence they can neither capture n...

Full description

Bibliographic Details
Main Authors: Shen, Jie, Zafeiriou, Stefanos, Chrysos, Grigorios G., Kossaifi, Jean, Tzimiropoulos, Georgios, Pantic, Maja
Format: Conference or Workshop Item
Published: 2015
Online Access:https://eprints.nottingham.ac.uk/31446/
_version_ 1848794204770140160
author Shen, Jie
Zafeiriou, Stefanos
Chrysos, Grigorios G.
Kossaifi, Jean
Tzimiropoulos, Georgios
Pantic, Maja
author_facet Shen, Jie
Zafeiriou, Stefanos
Chrysos, Grigorios G.
Kossaifi, Jean
Tzimiropoulos, Georgios
Pantic, Maja
author_sort Shen, Jie
building Nottingham Research Data Repository
collection Online Access
description Detection and tracking of faces in image sequences is among the most well studied problems in the intersection of statistical machine learning and computer vision. Often, tracking and detection methodologies use a rigid representation to describe the facial region 1, hence they can neither capture nor exploit the non-rigid facial deformations, which are crucial for countless of applications (e.g., facial expression analysis, facial motion capture, high-performance face recognition etc.). Usually, the non-rigid deformations are captured by locating and tracking the position of a set of fiducial facial landmarks (e.g., eyes, nose, mouth etc.). Recently, we witnessed a burst of research in automatic facial landmark localisation in static imagery. This is partly attributed to the availability of large amount of annotated data, many of which have been provided by the first facial landmark localisation challenge (also known as 300-W challenge). Even though now well established benchmarks exist for facial landmark localisation in static imagery, to the best of our knowledge, there is no established benchmark for assessing the performance of facial landmark tracking methodologies, containing an adequate number of annotated face videos. In conjunction with ICCV’2015 we run the first competition/challenge on facial landmark tracking in long-term videos. In this paper, we present the first benchmark for long-term facial landmark tracking, containing currently over 110 annotated videos, and we summarise the results of the competition.
first_indexed 2025-11-14T19:12:29Z
format Conference or Workshop Item
id nottingham-31446
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:12:29Z
publishDate 2015
recordtype eprints
repository_type Digital Repository
spelling nottingham-314462020-05-04T20:06:16Z https://eprints.nottingham.ac.uk/31446/ The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results Shen, Jie Zafeiriou, Stefanos Chrysos, Grigorios G. Kossaifi, Jean Tzimiropoulos, Georgios Pantic, Maja Detection and tracking of faces in image sequences is among the most well studied problems in the intersection of statistical machine learning and computer vision. Often, tracking and detection methodologies use a rigid representation to describe the facial region 1, hence they can neither capture nor exploit the non-rigid facial deformations, which are crucial for countless of applications (e.g., facial expression analysis, facial motion capture, high-performance face recognition etc.). Usually, the non-rigid deformations are captured by locating and tracking the position of a set of fiducial facial landmarks (e.g., eyes, nose, mouth etc.). Recently, we witnessed a burst of research in automatic facial landmark localisation in static imagery. This is partly attributed to the availability of large amount of annotated data, many of which have been provided by the first facial landmark localisation challenge (also known as 300-W challenge). Even though now well established benchmarks exist for facial landmark localisation in static imagery, to the best of our knowledge, there is no established benchmark for assessing the performance of facial landmark tracking methodologies, containing an adequate number of annotated face videos. In conjunction with ICCV’2015 we run the first competition/challenge on facial landmark tracking in long-term videos. In this paper, we present the first benchmark for long-term facial landmark tracking, containing currently over 110 annotated videos, and we summarise the results of the competition. 2015-12 Conference or Workshop Item PeerReviewed Shen, Jie, Zafeiriou, Stefanos, Chrysos, Grigorios G., Kossaifi, Jean, Tzimiropoulos, Georgios and Pantic, Maja (2015) The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results. In: 2015 IEEE International Conference on Computer Vision, 7-13 Dec 2015, Chile. http://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w25/html/Shen_The_First_Facial_ICCV_2015_paper.html
spellingShingle Shen, Jie
Zafeiriou, Stefanos
Chrysos, Grigorios G.
Kossaifi, Jean
Tzimiropoulos, Georgios
Pantic, Maja
The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results
title The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results
title_full The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results
title_fullStr The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results
title_full_unstemmed The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results
title_short The first Facial Landmark Tracking in-the-Wild Challenge: benchmark and results
title_sort first facial landmark tracking in-the-wild challenge: benchmark and results
url https://eprints.nottingham.ac.uk/31446/
https://eprints.nottingham.ac.uk/31446/