Touching the Void - Introducing CoST: Corpus of Social Touch

Merel Madeleine Jung, Ronald Walter Poppe, Mannes Poel, Dirk K.J. Heylen

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    21 Citations (Scopus)
    93 Downloads (Pure)

    Abstract

    Touch behavior is of great importance during social interaction. To transfer the tactile modality from interpersonal interaction to other areas such as Human-Robot Interaction (HRI) and remote communication automatic recognition of social touch is necessary. This paper introduces CoST: Corpus of Social Touch, a collection containing 7805 instances of 14 different social touch gestures. The gestures were performed in three variations: gentle, normal and rough, on a sensor grid wrapped around a mannequin arm. Recognition of the rough variations of these 14 gesture classes using Bayesian classifiers and Support Vector Machines (SVMs) resulted in an overall accuracy of 54% and 53%, respectively. Furthermore, this paper provides more insight into the challenges of automatic recognition of social touch gestures, including which gestures can be recognized more easily and which are more difficult to recognize.
    Original languageUndefined
    Title of host publicationProceedings of the 16th International Conference on Multimodal Interaction, ICMI 2014
    Place of PublicationNew York
    PublisherAssociation for Computing Machinery (ACM)
    Pages120-127
    Number of pages8
    ISBN (Print)978-1-4503-2885-2
    DOIs
    Publication statusPublished - Nov 2014
    Event16th International Conference on Multimodal Interaction, ICMI 2014 - Istanbul, Turkey, Istanbul, Turkey
    Duration: 12 Nov 201416 Nov 2014
    Conference number: 16

    Publication series

    Name
    PublisherACM

    Conference

    Conference16th International Conference on Multimodal Interaction, ICMI 2014
    Abbreviated titleICMI
    CountryTurkey
    CityIstanbul
    Period12/11/1416/11/14
    Other12-16 November 2014

    Keywords

    • EWI-25280
    • Touch gesture recognition
    • METIS-309648
    • Touch corpus
    • IR-93288
    • Social Touch

    Cite this

    Jung, M. M., Poppe, R. W., Poel, M., & Heylen, D. K. J. (2014). Touching the Void - Introducing CoST: Corpus of Social Touch. In Proceedings of the 16th International Conference on Multimodal Interaction, ICMI 2014 (pp. 120-127). New York: Association for Computing Machinery (ACM). https://doi.org/10.1145/2663204.2663242
    Jung, Merel Madeleine ; Poppe, Ronald Walter ; Poel, Mannes ; Heylen, Dirk K.J. / Touching the Void - Introducing CoST: Corpus of Social Touch. Proceedings of the 16th International Conference on Multimodal Interaction, ICMI 2014. New York : Association for Computing Machinery (ACM), 2014. pp. 120-127
    @inproceedings{5819863a356d460c99b9855ab1d7ff8a,
    title = "Touching the Void - Introducing CoST: Corpus of Social Touch",
    abstract = "Touch behavior is of great importance during social interaction. To transfer the tactile modality from interpersonal interaction to other areas such as Human-Robot Interaction (HRI) and remote communication automatic recognition of social touch is necessary. This paper introduces CoST: Corpus of Social Touch, a collection containing 7805 instances of 14 different social touch gestures. The gestures were performed in three variations: gentle, normal and rough, on a sensor grid wrapped around a mannequin arm. Recognition of the rough variations of these 14 gesture classes using Bayesian classifiers and Support Vector Machines (SVMs) resulted in an overall accuracy of 54{\%} and 53{\%}, respectively. Furthermore, this paper provides more insight into the challenges of automatic recognition of social touch gestures, including which gestures can be recognized more easily and which are more difficult to recognize.",
    keywords = "EWI-25280, Touch gesture recognition, METIS-309648, Touch corpus, IR-93288, Social Touch",
    author = "Jung, {Merel Madeleine} and Poppe, {Ronald Walter} and Mannes Poel and Heylen, {Dirk K.J.}",
    note = "10.1145/2663204.2663242",
    year = "2014",
    month = "11",
    doi = "10.1145/2663204.2663242",
    language = "Undefined",
    isbn = "978-1-4503-2885-2",
    publisher = "Association for Computing Machinery (ACM)",
    pages = "120--127",
    booktitle = "Proceedings of the 16th International Conference on Multimodal Interaction, ICMI 2014",
    address = "United States",

    }

    Jung, MM, Poppe, RW, Poel, M & Heylen, DKJ 2014, Touching the Void - Introducing CoST: Corpus of Social Touch. in Proceedings of the 16th International Conference on Multimodal Interaction, ICMI 2014. Association for Computing Machinery (ACM), New York, pp. 120-127, 16th International Conference on Multimodal Interaction, ICMI 2014, Istanbul, Turkey, 12/11/14. https://doi.org/10.1145/2663204.2663242

    Touching the Void - Introducing CoST: Corpus of Social Touch. / Jung, Merel Madeleine; Poppe, Ronald Walter; Poel, Mannes; Heylen, Dirk K.J.

    Proceedings of the 16th International Conference on Multimodal Interaction, ICMI 2014. New York : Association for Computing Machinery (ACM), 2014. p. 120-127.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    TY - GEN

    T1 - Touching the Void - Introducing CoST: Corpus of Social Touch

    AU - Jung, Merel Madeleine

    AU - Poppe, Ronald Walter

    AU - Poel, Mannes

    AU - Heylen, Dirk K.J.

    N1 - 10.1145/2663204.2663242

    PY - 2014/11

    Y1 - 2014/11

    N2 - Touch behavior is of great importance during social interaction. To transfer the tactile modality from interpersonal interaction to other areas such as Human-Robot Interaction (HRI) and remote communication automatic recognition of social touch is necessary. This paper introduces CoST: Corpus of Social Touch, a collection containing 7805 instances of 14 different social touch gestures. The gestures were performed in three variations: gentle, normal and rough, on a sensor grid wrapped around a mannequin arm. Recognition of the rough variations of these 14 gesture classes using Bayesian classifiers and Support Vector Machines (SVMs) resulted in an overall accuracy of 54% and 53%, respectively. Furthermore, this paper provides more insight into the challenges of automatic recognition of social touch gestures, including which gestures can be recognized more easily and which are more difficult to recognize.

    AB - Touch behavior is of great importance during social interaction. To transfer the tactile modality from interpersonal interaction to other areas such as Human-Robot Interaction (HRI) and remote communication automatic recognition of social touch is necessary. This paper introduces CoST: Corpus of Social Touch, a collection containing 7805 instances of 14 different social touch gestures. The gestures were performed in three variations: gentle, normal and rough, on a sensor grid wrapped around a mannequin arm. Recognition of the rough variations of these 14 gesture classes using Bayesian classifiers and Support Vector Machines (SVMs) resulted in an overall accuracy of 54% and 53%, respectively. Furthermore, this paper provides more insight into the challenges of automatic recognition of social touch gestures, including which gestures can be recognized more easily and which are more difficult to recognize.

    KW - EWI-25280

    KW - Touch gesture recognition

    KW - METIS-309648

    KW - Touch corpus

    KW - IR-93288

    KW - Social Touch

    U2 - 10.1145/2663204.2663242

    DO - 10.1145/2663204.2663242

    M3 - Conference contribution

    SN - 978-1-4503-2885-2

    SP - 120

    EP - 127

    BT - Proceedings of the 16th International Conference on Multimodal Interaction, ICMI 2014

    PB - Association for Computing Machinery (ACM)

    CY - New York

    ER -

    Jung MM, Poppe RW, Poel M, Heylen DKJ. Touching the Void - Introducing CoST: Corpus of Social Touch. In Proceedings of the 16th International Conference on Multimodal Interaction, ICMI 2014. New York: Association for Computing Machinery (ACM). 2014. p. 120-127 https://doi.org/10.1145/2663204.2663242