300 Faces In-The-Wild Challenge: database and results

Christos Sagonas, Epameinondas Antonakos, Georgios Tzimiropoulos, Stefanos Zafeiriou, Maja Pantic

    Research output: Contribution to journalArticleAcademicpeer-review

    179 Citations (Scopus)

    Abstract

    Computer Vision has recently witnessed great research advance towards automatic facial points detection. Numerous methodologies have been proposed during the last few years that achieve accurate and efficient performance. However, fair comparison between these methodologies is infeasible mainly due to two issues. (a) Most existing databases, captured under both constrained and unconstrained (in-the-wild) conditions have been annotated using different mark-ups and, in most cases, the accuracy of the annotations is low. (b) Most published works report experimental results using different training/testing sets, different error metrics and, of course, landmark points with semantically different locations. In this paper, we aim to overcome the aforementioned problems by (a) proposing a semi-automatic annotation technique that was employed to re-annotate most existing facial databases under a unified protocol, and (b) presenting the 300 Faces In-The-Wild Challenge (300-W), the first facial landmark localization challenge that was organized twice, in 2013 and 2015. To the best of our knowledge, this is the first effort towards a unified annotation scheme of massive databases and a fair experimental comparison of existing facial landmark localization systems. The images and annotations of the new testing database that was used in the 300-W challenge are available from http://ibug.doc.ic.ac.uk/resources/300-W_IMAVIS/.
    Original languageUndefined
    Pages (from-to)3-18
    Number of pages16
    JournalImage and vision computing
    Volume47
    DOIs
    Publication statusPublished - Mar 2016

    Keywords

    • EC Grant Agreement nr.: FP7/645094
    • HMI-HF: Human Factors
    • EWI-27127
    • IR-103792
    • Facial database
    • Facial landmark localization
    • Semi-automatic annotation tool
    • Challenge

    Cite this

    Sagonas, C., Antonakos, E., Tzimiropoulos, G., Zafeiriou, S., & Pantic, M. (2016). 300 Faces In-The-Wild Challenge: database and results. Image and vision computing, 47, 3-18. https://doi.org/10.1016/j.imavis.2016.01.002
    Sagonas, Christos ; Antonakos, Epameinondas ; Tzimiropoulos, Georgios ; Zafeiriou, Stefanos ; Pantic, Maja. / 300 Faces In-The-Wild Challenge: database and results. In: Image and vision computing. 2016 ; Vol. 47. pp. 3-18.
    @article{c36e0ef52ae6421abbebdde40e424265,
    title = "300 Faces In-The-Wild Challenge: database and results",
    abstract = "Computer Vision has recently witnessed great research advance towards automatic facial points detection. Numerous methodologies have been proposed during the last few years that achieve accurate and efficient performance. However, fair comparison between these methodologies is infeasible mainly due to two issues. (a) Most existing databases, captured under both constrained and unconstrained (in-the-wild) conditions have been annotated using different mark-ups and, in most cases, the accuracy of the annotations is low. (b) Most published works report experimental results using different training/testing sets, different error metrics and, of course, landmark points with semantically different locations. In this paper, we aim to overcome the aforementioned problems by (a) proposing a semi-automatic annotation technique that was employed to re-annotate most existing facial databases under a unified protocol, and (b) presenting the 300 Faces In-The-Wild Challenge (300-W), the first facial landmark localization challenge that was organized twice, in 2013 and 2015. To the best of our knowledge, this is the first effort towards a unified annotation scheme of massive databases and a fair experimental comparison of existing facial landmark localization systems. The images and annotations of the new testing database that was used in the 300-W challenge are available from http://ibug.doc.ic.ac.uk/resources/300-W_IMAVIS/.",
    keywords = "EC Grant Agreement nr.: FP7/645094, HMI-HF: Human Factors, EWI-27127, IR-103792, Facial database, Facial landmark localization, Semi-automatic annotation tool, Challenge",
    author = "Christos Sagonas and Epameinondas Antonakos and Georgios Tzimiropoulos and Stefanos Zafeiriou and Maja Pantic",
    year = "2016",
    month = "3",
    doi = "10.1016/j.imavis.2016.01.002",
    language = "Undefined",
    volume = "47",
    pages = "3--18",
    journal = "Image and vision computing",
    issn = "0262-8856",
    publisher = "Elsevier",

    }

    Sagonas, C, Antonakos, E, Tzimiropoulos, G, Zafeiriou, S & Pantic, M 2016, '300 Faces In-The-Wild Challenge: database and results', Image and vision computing, vol. 47, pp. 3-18. https://doi.org/10.1016/j.imavis.2016.01.002

    300 Faces In-The-Wild Challenge: database and results. / Sagonas, Christos; Antonakos, Epameinondas; Tzimiropoulos, Georgios; Zafeiriou, Stefanos; Pantic, Maja.

    In: Image and vision computing, Vol. 47, 03.2016, p. 3-18.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - 300 Faces In-The-Wild Challenge: database and results

    AU - Sagonas, Christos

    AU - Antonakos, Epameinondas

    AU - Tzimiropoulos, Georgios

    AU - Zafeiriou, Stefanos

    AU - Pantic, Maja

    PY - 2016/3

    Y1 - 2016/3

    N2 - Computer Vision has recently witnessed great research advance towards automatic facial points detection. Numerous methodologies have been proposed during the last few years that achieve accurate and efficient performance. However, fair comparison between these methodologies is infeasible mainly due to two issues. (a) Most existing databases, captured under both constrained and unconstrained (in-the-wild) conditions have been annotated using different mark-ups and, in most cases, the accuracy of the annotations is low. (b) Most published works report experimental results using different training/testing sets, different error metrics and, of course, landmark points with semantically different locations. In this paper, we aim to overcome the aforementioned problems by (a) proposing a semi-automatic annotation technique that was employed to re-annotate most existing facial databases under a unified protocol, and (b) presenting the 300 Faces In-The-Wild Challenge (300-W), the first facial landmark localization challenge that was organized twice, in 2013 and 2015. To the best of our knowledge, this is the first effort towards a unified annotation scheme of massive databases and a fair experimental comparison of existing facial landmark localization systems. The images and annotations of the new testing database that was used in the 300-W challenge are available from http://ibug.doc.ic.ac.uk/resources/300-W_IMAVIS/.

    AB - Computer Vision has recently witnessed great research advance towards automatic facial points detection. Numerous methodologies have been proposed during the last few years that achieve accurate and efficient performance. However, fair comparison between these methodologies is infeasible mainly due to two issues. (a) Most existing databases, captured under both constrained and unconstrained (in-the-wild) conditions have been annotated using different mark-ups and, in most cases, the accuracy of the annotations is low. (b) Most published works report experimental results using different training/testing sets, different error metrics and, of course, landmark points with semantically different locations. In this paper, we aim to overcome the aforementioned problems by (a) proposing a semi-automatic annotation technique that was employed to re-annotate most existing facial databases under a unified protocol, and (b) presenting the 300 Faces In-The-Wild Challenge (300-W), the first facial landmark localization challenge that was organized twice, in 2013 and 2015. To the best of our knowledge, this is the first effort towards a unified annotation scheme of massive databases and a fair experimental comparison of existing facial landmark localization systems. The images and annotations of the new testing database that was used in the 300-W challenge are available from http://ibug.doc.ic.ac.uk/resources/300-W_IMAVIS/.

    KW - EC Grant Agreement nr.: FP7/645094

    KW - HMI-HF: Human Factors

    KW - EWI-27127

    KW - IR-103792

    KW - Facial database

    KW - Facial landmark localization

    KW - Semi-automatic annotation tool

    KW - Challenge

    U2 - 10.1016/j.imavis.2016.01.002

    DO - 10.1016/j.imavis.2016.01.002

    M3 - Article

    VL - 47

    SP - 3

    EP - 18

    JO - Image and vision computing

    JF - Image and vision computing

    SN - 0262-8856

    ER -

    Sagonas C, Antonakos E, Tzimiropoulos G, Zafeiriou S, Pantic M. 300 Faces In-The-Wild Challenge: database and results. Image and vision computing. 2016 Mar;47:3-18. https://doi.org/10.1016/j.imavis.2016.01.002