Alignment by Composition

@article{Sevilmis2019AlignmentBC,
  title={Alignment by Composition},
  author={Berk Sevilmis and Benjamin B. Kimia},
  journal={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2019},
  pages={2009-2018}
}
  • Berk Sevilmis, Benjamin B. Kimia
  • Published in
    IEEE Winter Conference on…
    2019
  • Computer Science
  • We propose an unsupervised method to establish dense semantic correspondences between images depicting different instances of the same object category. We posit that alignment is compositional in nature and requires the detection of a similar visual concept between images. We realize this in a top-down fashion using objectness, saliency, and visual similarity cues to co-localize the regions of holistic foreground objects. Jointly maximizing visual similarity and bounding the geometric… CONTINUE READING

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

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES

    Proposal Flow: Semantic Correspondences from Object Proposals

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Convolutional Neural Network Architecture for Geometric Matching

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Joint Recovery of Dense Correspondence and Cosegmentation in Two Images

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Scale-Space SIFT flow

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Deformable Spatial Pyramid Matching for Fast Dense Correspondences

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    SIFT Flow: Dense Correspondence across Scenes and Its Applications

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    DCTM: Discrete-Continuous Transformation Matching for Semantic Flow

    VIEW 1 EXCERPT

    Deep Semantic Feature Matching

    VIEW 1 EXCERPT