Learning multi-scale sparse representation for visual tracking

Zhengjian Kang, Edward Wong

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

    Abstract

    We present a novel algorithm for learning multi-scale sparse representation for visual tracking. In our method, sparse codes with max pooling are used to form a multi-scale representation that integrates spatial configuration over patches of different sizes. Different from other sparse representation methods, our method uses both holistic and local descriptors. In the hybrid framework, we formulate a new confidence measure that combines generative and discriminative confidence scores. We also devised an efficient method to update templates for adaptation to appearance changes. We demonstrate the effectiveness of our method with experiments and show that our method outperforms other state-of-the-art tracking algorithms.

    Original languageEnglish (US)
    Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages4897-4901
    Number of pages5
    ISBN (Print)9781479957514
    DOIs
    StatePublished - Jan 28 2014

    Fingerprint

    Experiments

    Keywords

    • max pooling
    • Multi-scale sparse representation
    • visual tracking

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition

    Cite this

    Kang, Z., & Wong, E. (2014). Learning multi-scale sparse representation for visual tracking. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 4897-4901). [7025992] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025992

    Learning multi-scale sparse representation for visual tracking. / Kang, Zhengjian; Wong, Edward.

    2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 4897-4901 7025992.

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

    Kang, Z & Wong, E 2014, Learning multi-scale sparse representation for visual tracking. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025992, Institute of Electrical and Electronics Engineers Inc., pp. 4897-4901. https://doi.org/10.1109/ICIP.2014.7025992
    Kang Z, Wong E. Learning multi-scale sparse representation for visual tracking. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 4897-4901. 7025992 https://doi.org/10.1109/ICIP.2014.7025992
    Kang, Zhengjian ; Wong, Edward. / Learning multi-scale sparse representation for visual tracking. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 4897-4901
    @inproceedings{ef81e4bc1e544ad69f457851ccdafd68,
    title = "Learning multi-scale sparse representation for visual tracking",
    abstract = "We present a novel algorithm for learning multi-scale sparse representation for visual tracking. In our method, sparse codes with max pooling are used to form a multi-scale representation that integrates spatial configuration over patches of different sizes. Different from other sparse representation methods, our method uses both holistic and local descriptors. In the hybrid framework, we formulate a new confidence measure that combines generative and discriminative confidence scores. We also devised an efficient method to update templates for adaptation to appearance changes. We demonstrate the effectiveness of our method with experiments and show that our method outperforms other state-of-the-art tracking algorithms.",
    keywords = "max pooling, Multi-scale sparse representation, visual tracking",
    author = "Zhengjian Kang and Edward Wong",
    year = "2014",
    month = "1",
    day = "28",
    doi = "10.1109/ICIP.2014.7025992",
    language = "English (US)",
    isbn = "9781479957514",
    pages = "4897--4901",
    booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Learning multi-scale sparse representation for visual tracking

    AU - Kang, Zhengjian

    AU - Wong, Edward

    PY - 2014/1/28

    Y1 - 2014/1/28

    N2 - We present a novel algorithm for learning multi-scale sparse representation for visual tracking. In our method, sparse codes with max pooling are used to form a multi-scale representation that integrates spatial configuration over patches of different sizes. Different from other sparse representation methods, our method uses both holistic and local descriptors. In the hybrid framework, we formulate a new confidence measure that combines generative and discriminative confidence scores. We also devised an efficient method to update templates for adaptation to appearance changes. We demonstrate the effectiveness of our method with experiments and show that our method outperforms other state-of-the-art tracking algorithms.

    AB - We present a novel algorithm for learning multi-scale sparse representation for visual tracking. In our method, sparse codes with max pooling are used to form a multi-scale representation that integrates spatial configuration over patches of different sizes. Different from other sparse representation methods, our method uses both holistic and local descriptors. In the hybrid framework, we formulate a new confidence measure that combines generative and discriminative confidence scores. We also devised an efficient method to update templates for adaptation to appearance changes. We demonstrate the effectiveness of our method with experiments and show that our method outperforms other state-of-the-art tracking algorithms.

    KW - max pooling

    KW - Multi-scale sparse representation

    KW - visual tracking

    UR - http://www.scopus.com/inward/record.url?scp=84949928355&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84949928355&partnerID=8YFLogxK

    U2 - 10.1109/ICIP.2014.7025992

    DO - 10.1109/ICIP.2014.7025992

    M3 - Conference contribution

    SN - 9781479957514

    SP - 4897

    EP - 4901

    BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -