Automatic Image Annotation and Retrieval using Multi-Instance Multi-Label Learning

  title={Automatic Image Annotation and Retrieval using Multi-Instance Multi-Label Learning},
  author={T. Sumathi and C. Lakshmi Devasena and R. Revathi and S Gokula Priya and Dr.M. Hemalatha},
In this paper, we propose the MIML (Multi- Instance Multi-Label learning) framework which is associated with multiple class labels for Image Annotation. Compared to traditional learning frameworks, the MIML framework is more convenient and natural for representing complicated objects which have multiple semantic meanings. To learn from MIML examples we have taken a survey on MIML Boost, MIMLSVM, D-MIMLSVM, InsDif and SubCod algorithms. MIML Boost and MIML SVM are based on a simple degeneration… CONTINUE READING

Figures and Topics from this paper.

Similar Papers


Publications referenced by this paper.

Multi - instance kernels Solving multi - instance problems with classifier ensemble based on constructive clustering

P. A. Flach, A. Kowalczyk, A. J. Smola
  • Knowledge and Information Systems
  • 2007

, and M . Pontil . Learning multiple tasks with kernel methods

C. A. Micchelli Evgeniou
  • Journal of Machine Learning Research
  • 2005

Support vector machines for multiple - instance learning

M. Craven Settles, S. Ray, +3 authors S. Roweis
  • Advances in Neural Information Processing Systems
  • 2003

Image database retrieval with multiple-instance learning techniques

  • Proceedings of 16th International Conference on Data Engineering (Cat. No.00CB37073)
  • 2000

Content - based image retrieval using multiple - instance learning

I. Tsochantaridis Andrews, T. Hofmann
  • Proceedings of the 19 th International Conference on Machine Learning