BIROn - Birkbeck Institutional Research Online

    Learning attentions: residual attentional Siamese Network for high performance online visual tracking

    Wang, Q. and Teng, Z. and Xing, J. and Gao, J. and Hu, W. and Maybank, Stephen J. (2018) Learning attentions: residual attentional Siamese Network for high performance online visual tracking. IEEE Computer Society Conference on Computer Vision and Pattern Recognition , ISSN 1063-6919.

    21761.pdf - Author's Accepted Manuscript

    Download (4MB) | Preview


    Offline training for object tracking has recently shown great potentials in balancing tracking accuracy and speed. However, it is still difficult to adapt an offline trained model to a target tracked online. This work presents a Residual Attentional Siamese Network (RASNet) for high performance object tracking. The RASNet model reformulates the correlation filter within a Siamese tracking framework, and introduces different kinds of the attention mechanisms to adapt the model without updating the model online. In particular, by exploiting the offline trained general attention, the target adapted residual attention, and the channel favored feature attention, the RASNet not only mitigates the over-fitting problem in deep network training, but also enhances its discriminative capacity and adaptability due to the separation of representation learning and discriminator learning. The proposed deep architecture is trained from end to end and takes full advantage of the rich spatial temporal information to achieve robust visual tracking. Experimental results on two latest benchmarks, OTB-2015 and VOT2017, show that the RASNet tracker has the state-of-the-art tracking accuracy while runs at more than 80 frames per second.


    Item Type: Article
    Additional Information: (c) 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Administrator
    Date Deposited: 20 Mar 2018 14:20
    Last Modified: 12 Apr 2022 18:04


    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