Achieving semantic coupling in the domain of high-dimensional video indexing application

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 4305, Issue , 2001, Pages 97-107

  Mittal, A ^a   Cheong, L F ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Dimensionality reduction; Elemental characterization; Fast training; Multimedia indexing; Neural networks; Optimum weight assignment; Relevant features evaluation; Support vector machines

Indexed keywords

CONTENT BASED RETRIEVAL; DATABASE SYSTEMS; INDEXING (OF INFORMATION); MULTIMEDIA SYSTEMS; NEURAL NETWORKS;

MULTIMEDIA INDEXING; SUPPORT VECTOR MACHINES (SVM);

SEMANTICS;

EID: 0034942826     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.420931     Document Type: Conference Paper

References (23)

1. A survey of technologies for parsing and indexing digital video
2. How good are support vector machines?
3. A critical overview of neural network pattern classifiers
4. On the use of support vector machines for phonetic classification
5. Target classification via support vector machines
6. A tutorial on support vector machines for pattern recognition
7. Semantic modeling and knowledge representation in multimedia databases
8. Feature selection for case-based classification of cloud types: An empirical comparison
9. Dimensionality reduction via discretization
10. A critical evaluation of intrinsic dimensionality reduction algorithms
11. Selection using rough sets theory
12. Learning boolean concepts in the presence of many irrelevant features
13. Reducing misclassification costs
14. An interative improvement approach for the discretization of numeric attributes in bayesian classifiers
15. Bounds on the bayes classification error based on pairwise risk functions
16. Estimating the bayes error rate through classifier combining
17. A class discrimability measure based on feature space partitioning