BIROn - Birkbeck Institutional Research Online

    Modeling geometric-temporal context with directional pyramid co-occurrence for action recognition

    Yuan, C. and Li, X. and Hu, W. and Ling, H. and Maybank, Stephen J. (2014) Modeling geometric-temporal context with directional pyramid co-occurrence for action recognition. IEEE Transactions on Image Processing 23 (2), pp. 658-672. ISSN 1057-7149.

    [img]
    Preview
    Text
    13350.pdf - Author's Accepted Manuscript

    Download (1MB) | Preview

    Abstract

    In this paper, we present a new geometric-temporal representation for visual action recognition based on local spatio-temporal features. First, we propose a modified covariance descriptor under the log-Euclidean Riemannian metric to represent the spatio-temporal cuboids detected in the video sequences. Compared with previously proposed covariance descriptors, our descriptor can be measured and clustered in Euclidian space. Second, to capture the geometric-temporal contextual information, we construct a directional pyramid co-occurrence matrix (DPCM) to describe the spatio-temporal distribution of the vector-quantized local feature descriptors extracted from a video. DPCM characterizes the co-occurrence statistics of local features as well as the spatio-temporal positional relationships among the concurrent features. These statistics provide strong descriptive power for action recognition. To use DPCM for action recognition, we propose a directional pyramid co-occurrence matching kernel to measure the similarity of videos. The proposed method achieves the state-of-the-art performance and improves on the recognition performance of the bag-of-visual-words (BOVWs) models by a large margin on six public data sets. For example, on the KTH data set, it achieves 98.78% accuracy while the BOVW approach only achieves 88.06%. On both Weizmann and UCF CIL data sets, the highest possible accuracy of 100% is achieved.

    Metadata

    Item Type: Article
    Additional Information: (c) 2014 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: Birkbeck Schools and Departments > School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Administrator
    Date Deposited: 05 Nov 2015 11:18
    Last Modified: 05 Nov 2015 11:18
    URI: http://eprints.bbk.ac.uk/id/eprint/13350

    Statistics

    Downloads
    Activity Overview
    127Downloads
    121Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item