Recent trends in image understanding have pushed for holistic scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning, and local appearance based classifiers. In this work, we are interested in understanding the roles of these different tasks in improved scene understanding, in particular semantic segmentation, object detection and scene recognition. Towards this goal, we “plug-in” human subjects for each of the various components in a state-of-the-art conditional random field model. Comparisons among various hybrid human-machine CRFs give us indications of how much “head room” there is to improve scene understanding by focusing research efforts on various individual tasks.


    Access

    Download


    Export, share and cite



    Title :

    Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding


    Contributors:

    Publication date :

    2014


    Remarks:

    arXiv:1406.3906


    Type of media :

    Report , Paper


    Type of material :

    Electronic Resource


    Language :

    English





    Vision-Based Holistic Scene Understanding for Context-Aware Human-Robot Interaction

    Giorgio De Magistris / Riccardo Caprari / Giulia Castro et al. | BASE | 2022

    Free access

    Inference Methods for CRFs with Co-occurrence Statistics

    Ladický, u. / Russell, C. / Kohli, P. et al. | British Library Online Contents | 2013


    RvGIST: A Holistic Road Feature for Real-Time Road-Scene Understanding

    Sun, Yuan / Lu, Hongbo / Zhang, Zhimin | IEEE | 2013


    METHOD AND APPARATUS FOR IDENTIFYING CONGESTION BOTTLENECKS

    HALAMA CHRISTIAN / CURRAN STEPHEN / COOMANS TOMAS et al. | European Patent Office | 2019

    Free access

    METHOD AND APPARATUS FOR IDENTIFYING CONGESTION BOTTLENECKS

    HALAMA CHRISTIAN / CURRAN STEPHEN / COOMANS TOMAS et al. | European Patent Office | 2017

    Free access