From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model

@article{Chang2011FromCT,
  title={From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model},
  author={Kai-Yueh Chang and Tyng-Luh Liu and Shang-Hong Lai},
  journal={CVPR 2011},
  year={2011},
  pages={2129-2136}
}
  • Kai-Yueh Chang, Tyng-Luh Liu, Shang-Hong Lai
  • Published in CVPR 2011
  • Computer Science
  • We address two key issues of co-segmentation over multiple images. The first is whether a pure unsupervised algorithm can satisfactorily solve this problem. Without the user's guidance, segmenting the foregrounds implied by the common object is quite a challenging task, especially when substantial variations in the object's appearance, shape, and scale are allowed. The second issue concerns the efficiency if the technique can lead to practical uses. With these in mind, we establish an MRF… 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 143 CITATIONS

    Co-attention CNNs for Unsupervised Object Co-segmentation

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Adaptive Features for MRF based Cosegmentation

    VIEW 14 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Co-Segmentation Guided Hough Transform for Robust Feature Matching

    VIEW 9 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Unsupervised co-segmentation based on a new global GMM constraint in MRF

    VIEW 8 EXCERPTS
    CITES METHODS, RESULTS & BACKGROUND
    HIGHLY INFLUENCED

    Cluster-Based Co-Saliency Detection

    VIEW 10 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A new co-saliency model via pairwise constraint graph matching

    VIEW 11 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Many-to-Many High Order Matching. Applications to Tracking and Object

    VIEW 11 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Group-wise Deep Co-saliency Detection

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2012
    2020

    CITATION STATISTICS

    • 20 Highly Influenced Citations

    • Averaged 15 Citations per year from 2017 through 2019

    • 82% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 31 REFERENCES

    Discriminative clustering for image co-segmentation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    An efficient algorithm for Co-segmentation

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Context-Aware Saliency Detection

    VIEW 2 EXCERPTS

    CVX: Matlab software for disciplined convex programming, version 1.21

    • M. Grant, S. Boyd
    • 2010
    VIEW 1 EXCERPT

    Geodesic star convexity for interactive image segmentation

    Preattentive co-saliency detection

    • Hwann-Tzong Chen
    • Computer Science
    • 2010 IEEE International Conference on Image Processing
    • 2010
    VIEW 1 EXCERPT