Learning the semantics of multimedia queries and concepts from a small number of examples

@inproceedings{Natsev2005LearningTS,
  title={Learning the semantics of multimedia queries and concepts from a small number of examples},
  author={Apostol Natsev and Milind R. Naphade and Jelena Tesic},
  booktitle={ACM Multimedia},
  year={2005}
}
In this paper we unify two supposedly distinct tasks in multimedia retrieval. One task involves answering queries with a few examples. The other involves learning models for semantic concepts, also with a few examples. In our view these two tasks are identical with the only differentiation being the number of examples that are available for training. Once we adopt this unified view, we then apply identical techniques for solving both problems and evaluate the performance using the NIST TRECVID… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • In particular, we observe an improvement of 6% for rare concept detection and 17% for the search task.

Citations

Publications citing this paper.
SHOWING 1-10 OF 123 CITATIONS, ESTIMATED 91% COVERAGE

Multigraph-Based Query-Independent Learning for Video Search

  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2009
VIEW 12 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

GKSH: Graph based Image Retrieval using Supervised Kernel Hashing

  • ICIMCS
  • 2016
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Content-based visual search learned from social media

Xirong Li
  • 2012
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

PISAR: Progressive image search and recommendation system by auto-interpretation and user behavior

  • 2011 IEEE International Conference on Systems, Man, and Cybernetics
  • 2011
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Data Modeling Strategies for Imbalanced Learning in Visual Search

  • 2007 IEEE International Conference on Multimedia and Expo
  • 2007
VIEW 5 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Video diver: generic video indexing with diverse features

  • Multimedia Information Retrieval
  • 2007
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Interactive content-based visualizations for multimedia search

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Bootstrapping Visual Categorization With Relevant Negatives

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Internet Multimedia Search and Mining

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2004
2018

CITATION STATISTICS

  • 17 Highly Influenced Citations

  • Averaged 2 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-9 OF 9 REFERENCES

Nature of Statistical Learning Theory

V. Vapnik.The
  • 1995
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

On the detection of semantic concepts at TRECVID

M. Naphade, J. Smith, F. Souvannavong
  • 2004
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Efficient Query Refinement in Multimedia Databases

  • Proceedings of 16th International Conference on Data Engineering (Cat. No.00CB37073)
  • 2000
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL