A study of synthesizing new human motions from sampled motions using Tensor Decomposition

Rovshan Kalanov, Jieun Cho, Jun Ohya

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    This paper applies an algorithm, based on Tensor Decomposition, to a new synthesis application: by using sampled motions of people of different ages under different emotional states, new motions for other people are synthesized. Human motion is the composite consequence of multiple elements, including the action performed and a motion signature that captures the distinctive pattern of movement of a particular individual. By performing decomposition, based on N-mode SVD (singular value decomposition), the algorithm analyzes motion data spanning multiple subjects performing different actions to extract these motion elements. The analysis yields a generative motion model that can synthesize new motions in the distinctive styles of these individuals. The effectiveness of applying the tensor decomposition approach to our purpose was confirmed by synthesizing novel walking motions for a person by using the extracted signature.

    Original languageEnglish
    Title of host publicationIEEE International Conference on Multimedia and Expo, ICME 2005
    Pages1326-1329
    Number of pages4
    Volume2005
    DOIs
    Publication statusPublished - 2005
    EventIEEE International Conference on Multimedia and Expo, ICME 2005 - Amsterdam
    Duration: 2005 Jul 62005 Jul 8

    Other

    OtherIEEE International Conference on Multimedia and Expo, ICME 2005
    CityAmsterdam
    Period05/7/605/7/8

    Fingerprint

    Tensors
    Singular value decomposition
    Composite materials

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Kalanov, R., Cho, J., & Ohya, J. (2005). A study of synthesizing new human motions from sampled motions using Tensor Decomposition. In IEEE International Conference on Multimedia and Expo, ICME 2005 (Vol. 2005, pp. 1326-1329). [1521674] https://doi.org/10.1109/ICME.2005.1521674

    A study of synthesizing new human motions from sampled motions using Tensor Decomposition. / Kalanov, Rovshan; Cho, Jieun; Ohya, Jun.

    IEEE International Conference on Multimedia and Expo, ICME 2005. Vol. 2005 2005. p. 1326-1329 1521674.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Kalanov, R, Cho, J & Ohya, J 2005, A study of synthesizing new human motions from sampled motions using Tensor Decomposition. in IEEE International Conference on Multimedia and Expo, ICME 2005. vol. 2005, 1521674, pp. 1326-1329, IEEE International Conference on Multimedia and Expo, ICME 2005, Amsterdam, 05/7/6. https://doi.org/10.1109/ICME.2005.1521674
    Kalanov R, Cho J, Ohya J. A study of synthesizing new human motions from sampled motions using Tensor Decomposition. In IEEE International Conference on Multimedia and Expo, ICME 2005. Vol. 2005. 2005. p. 1326-1329. 1521674 https://doi.org/10.1109/ICME.2005.1521674
    Kalanov, Rovshan ; Cho, Jieun ; Ohya, Jun. / A study of synthesizing new human motions from sampled motions using Tensor Decomposition. IEEE International Conference on Multimedia and Expo, ICME 2005. Vol. 2005 2005. pp. 1326-1329
    @inproceedings{ae29dcc200504cdcb6612f53d81246e1,
    title = "A study of synthesizing new human motions from sampled motions using Tensor Decomposition",
    abstract = "This paper applies an algorithm, based on Tensor Decomposition, to a new synthesis application: by using sampled motions of people of different ages under different emotional states, new motions for other people are synthesized. Human motion is the composite consequence of multiple elements, including the action performed and a motion signature that captures the distinctive pattern of movement of a particular individual. By performing decomposition, based on N-mode SVD (singular value decomposition), the algorithm analyzes motion data spanning multiple subjects performing different actions to extract these motion elements. The analysis yields a generative motion model that can synthesize new motions in the distinctive styles of these individuals. The effectiveness of applying the tensor decomposition approach to our purpose was confirmed by synthesizing novel walking motions for a person by using the extracted signature.",
    author = "Rovshan Kalanov and Jieun Cho and Jun Ohya",
    year = "2005",
    doi = "10.1109/ICME.2005.1521674",
    language = "English",
    isbn = "0780393325",
    volume = "2005",
    pages = "1326--1329",
    booktitle = "IEEE International Conference on Multimedia and Expo, ICME 2005",

    }

    TY - GEN

    T1 - A study of synthesizing new human motions from sampled motions using Tensor Decomposition

    AU - Kalanov, Rovshan

    AU - Cho, Jieun

    AU - Ohya, Jun

    PY - 2005

    Y1 - 2005

    N2 - This paper applies an algorithm, based on Tensor Decomposition, to a new synthesis application: by using sampled motions of people of different ages under different emotional states, new motions for other people are synthesized. Human motion is the composite consequence of multiple elements, including the action performed and a motion signature that captures the distinctive pattern of movement of a particular individual. By performing decomposition, based on N-mode SVD (singular value decomposition), the algorithm analyzes motion data spanning multiple subjects performing different actions to extract these motion elements. The analysis yields a generative motion model that can synthesize new motions in the distinctive styles of these individuals. The effectiveness of applying the tensor decomposition approach to our purpose was confirmed by synthesizing novel walking motions for a person by using the extracted signature.

    AB - This paper applies an algorithm, based on Tensor Decomposition, to a new synthesis application: by using sampled motions of people of different ages under different emotional states, new motions for other people are synthesized. Human motion is the composite consequence of multiple elements, including the action performed and a motion signature that captures the distinctive pattern of movement of a particular individual. By performing decomposition, based on N-mode SVD (singular value decomposition), the algorithm analyzes motion data spanning multiple subjects performing different actions to extract these motion elements. The analysis yields a generative motion model that can synthesize new motions in the distinctive styles of these individuals. The effectiveness of applying the tensor decomposition approach to our purpose was confirmed by synthesizing novel walking motions for a person by using the extracted signature.

    UR - http://www.scopus.com/inward/record.url?scp=33750570195&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=33750570195&partnerID=8YFLogxK

    U2 - 10.1109/ICME.2005.1521674

    DO - 10.1109/ICME.2005.1521674

    M3 - Conference contribution

    SN - 0780393325

    SN - 9780780393325

    VL - 2005

    SP - 1326

    EP - 1329

    BT - IEEE International Conference on Multimedia and Expo, ICME 2005

    ER -