Building contextual visual vocabulary for large-scale image applications

@inproceedings{Zhang2010BuildingCV,
  title={Building contextual visual vocabulary for large-scale image applications},
  author={Shiliang Zhang and Qingming Huang and Gang Hua and Shuqiang Jiang and Wen Gao and Qi Tian},
  booktitle={ACM Multimedia},
  year={2010}
}
Not withstanding its great success and wide adoption in Bag-of-visual Words representation, visual vocabulary created from single image local features is often shown to be ineffective largely due to three reasons. First, many detected local features are not stable enough, resulting in many noisy and non-descriptive visual words in images. Second, single visual word discards the rich spatial contextual information among the local features, which has been proven to be valuable for visual matching… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 103 CITATIONS, ESTIMATED 85% COVERAGE

Exploring Spatial Correlation for Visual Object Retrieval

  • ACM TIST
  • 2015
VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Content based video retrieval via spatial-temporal information discovery.

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Edge-SIFT: Discriminative Binary Descriptor for Scalable Partial-Duplicate Mobile Search

  • IEEE Transactions on Image Processing
  • 2013
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Exploiting visual word co-occurrence for image retrieval

VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Building descriptive and discriminative visual codebook for large-scale image applications

  • Multimedia Tools and Applications
  • 2010
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Randomized Spatial Context for Object Search

  • IEEE Transactions on Image Processing
  • 2015
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Cascade Category-Aware Visual Search

  • IEEE Transactions on Image Processing
  • 2014
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Embedding Multi-Order Spatial Clues for Scalable Visual Matching and Retrieval

  • IEEE Journal on Emerging and Selected Topics in Circuits and Systems
  • 2014
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Multi-order visual phrase for scalable partial-duplicate visual search

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

USB: Ultrashort Binary Descriptor for Fast Visual Matching and Retrieval

  • IEEE Transactions on Image Processing
  • 2014
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2010
2019

CITATION STATISTICS

  • 18 Highly Influenced Citations

  • Averaged 6 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 15 REFERENCES

VisualRank: Applying PageRank to Large-Scale Image Search

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2008
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Scalable Recognition with a Vocabulary Tree

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Metric Learning by Collapsing Classes

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Bundling features for large scale partial-duplicate web image search

  • 2009 IEEE Conference on Computer Vision and Pattern Recognition
  • 2009
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

ImageNet: A large-scale hierarchical image database

  • CVPR 2009
  • 2009
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…