• Computer Science
  • Published in ICLR 2015

Particular object retrieval with integral max-pooling of CNN activations

@article{Tolias2015ParticularOR,
  title={Particular object retrieval with integral max-pooling of CNN activations},
  author={Giorgos Tolias and Ronan Sicre and Herv{\'e} J{\'e}gou},
  journal={CoRR},
  year={2015},
  volume={abs/1511.05879}
}
Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 372 CITATIONS

Class-Weighted Convolutional Features for Visual Instance Search

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Deep Region Hashing for Generic Instance Search from Images

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Feature Reconstruction by Laplacian Eigenmaps for Efficient Instance Search

VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Fine-Grained Retrieval with Autoencoders

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 125 Highly Influenced Citations

  • Averaged 115 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 50 REFERENCES

From generic to specific deep representations for visual recognition

Azizpour, Hossein, +7 authors Stefan
  • In arXiv,
  • 2014
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Object retrieval with large vocabularies and fast spatial matching

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Fast Object Retrieval Using Direct Spatial Matching

  • IEEE Transactions on Multimedia
  • 2015
VIEW 1 EXCERPT
HIGHLY INFLUENTIAL

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2015
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL