BIROn - Birkbeck Institutional Research Online

    Do not lose the details: reinforced representation learning for high performance visual tracking

    Wang, Q. and Zhang, M. and Xing, J. and Gao, J. and Hu, W. and Maybank, Stephen J. (2018) Do not lose the details: reinforced representation learning for high performance visual tracking. In: Lang, J. (ed.) Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence. ISBN 9780999241127.

    VisualTrackingIJCAI2018.pdf - Author's Accepted Manuscript

    Download (1MB) | Preview


    This work presents a novel end-to-end trainable CNN model for high performance visual object tracking. It learns both low-level fine-grained representations and a high-level semantic embedding space in a mutual reinforced way, and a multi-task learning strategy is proposed to perform the correlation analysis on representations from both levels. In particular, a fully convolutional encoder-decoder network is designed to reconstruct the original visual features from the semantic projections to preserve all the geometric information. Moreover, the correlation filter layer working on the fine-grained representations leverages a global context constraint for accurate object appearance modeling. The correlation filter in this layer is updated online efficiently without network fine-tuning. Therefore, the proposed tracker benefits from two complementary effects: the adaptability of the fine-grained correlation analysis and the generalization capability of the semantic embedding. Extensive experimental evaluations on four popular benchmarks demonstrate its state-of-the-art performance.


    Item Type: Book Section
    Additional Information: IJCAI-ECAI-18, Stockholm, Sweden, July 13-19, 2018
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Stephen Maybank
    Date Deposited: 21 May 2018 13:47
    Last Modified: 07 Mar 2022 17:37


    Activity Overview
    6 month trend
    6 month trend

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item