Social negative bootstrapping for visual categorization

@inproceedings{Li2011SocialNB,
  title={Social negative bootstrapping for visual categorization},
  author={Xirong Li and Cees Snoek and Marcel Worring and Arnold W. M. Smeulders},
  booktitle={ICMR},
  year={2011}
}
To learn classifiers for many visual categories, obtaining labeled training examples in an efficient way is crucial. Since a classifier tends to misclassify negative examples which are visually similar to positive examples, inclusion of such informative negatives should be stressed in the learning process. However, they are unlikely to be hit by random sampling, the de facto standard in literature. In this paper, we go beyond random sampling by introducing a novel social negative bootstrapping… CONTINUE READING
Highly Cited
This paper has 22 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 1 time. VIEW TWEETS

From This Paper

Results and topics from this paper.

Key Quantitative Results

  • On a popular visual categorization benchmark our precision at 20 increases by 34%, compared to baselines trained on randomly sampled negatives.

Citations

Publications citing this paper.
Showing 1-10 of 17 extracted citations

Sampling and Ontologically Pooling Web Images for Visual Concept Learning

IEEE Transactions on Multimedia • 2012
View 4 Excerpts
Highly Influenced

Mining near duplicate image groups

Multimedia Tools and Applications • 2014
View 3 Excerpts

References

Publications referenced by this paper.
Showing 1-8 of 8 references

Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding • 2008
View 5 Excerpts
Highly Influenced

The Google Similarity Distance

IEEE Transactions on Knowledge and Data Engineering • 2007
View 4 Excerpts
Highly Influenced

Harvesting Image Databases from The Web

Snehal M. Gaikwad, G. H. Raisoni
2012
View 7 Excerpts
Highly Influenced

Learning automatic concept detectors from online video

Computer Vision and Image Understanding • 2010
View 5 Excerpts
Highly Influenced

ImageNet: A large-scale hierarchical image database

2009 IEEE Conference on Computer Vision and Pattern Recognition • 2009
View 7 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…