Object recognition with hierarchical kernel descriptors

@article{Bo2011ObjectRW,
  title={Object recognition with hierarchical kernel descriptors},
  author={Liefeng Bo and Kevin Lai and Xiaofeng Ren and Dieter Fox},
  journal={CVPR 2011},
  year={2011},
  pages={1729-1736}
}
  • Liefeng Bo, Kevin Lai, +1 author Dieter Fox
  • Published in CVPR 2011
  • Computer Science
  • Kernel descriptors [1] provide a unified way to generate rich visual feature sets by turning pixel attributes into patch-level features, and yield impressive results on many object recognition tasks. However, best results with kernel descriptors are achieved using efficient match kernels in conjunction with nonlinear SVMs, which makes it impractical for large-scale problems. In this paper, we propose hierarchical kernel descriptors that apply kernel descriptors recursively to form image-level… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 191 CITATIONS

    Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection

    VIEW 9 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    of Local Descriptor in RGB-D Object Recognition

    VIEW 14 EXCERPTS
    CITES METHODS, BACKGROUND & RESULTS
    HIGHLY INFLUENCED

    Convolutional Kernel Networks

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Efficient image representation for object recognition via pivots selection

    VIEW 10 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Kernel Descriptors in comparison with Hierarchical Matching Pursuit

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    3D convolutional object recognition using volumetric representations of depth data

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Combining features for RGB-D object recognition

    VIEW 4 EXCERPTS
    CITES RESULTS, BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Object recognition from 3D depth data with Extreme Learning Machine and Local Receptive Field

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A Gestaltist approach to contour-based object recognition: Combining bottom-up and top-down cues

    VIEW 5 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2010
    2020

    CITATION STATISTICS

    • 14 Highly Influenced Citations

    • Averaged 19 Citations per year from 2017 through 2019

    • 8% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES

    A large-scale hierarchical multi-view RGB-D object dataset

    VIEW 10 EXCERPTS

    Histograms of oriented gradients for human detection

    • Navneet Dalal, Bill Triggs
    • Computer Science
    • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
    • 2005
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    An analysis of single-layer networks in unsupervised feature learning

    • A. Coates, H. Lee, A. Ng
    • In NIPS*2010 Workshop on Deep Learning,
    • 2010
    VIEW 2 EXCERPTS

    Locality-constrained Linear Coding for image classification

    VIEW 1 EXCERPT