Applying genetic algorithms to query optimization in document retrieval
Information Processing and Management: an International Journal
The Journal of Machine Learning Research
PLSA-based image auto-annotation: constraining the latent space
Proceedings of the 12th annual ACM international conference on Multimedia
Formulating Semantic Image Annotation as a Supervised Learning Problem
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Enhancing relevance scoring with chronological term rank
SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
Structural optimization of a full-text n-gram index using relational normalization
The VLDB Journal — The International Journal on Very Large Data Bases
Compressing term positions in web indexes
Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Lexical Chains Segmentation in Summarization
SYNASC '08 Proceedings of the 2008 10th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing
A Bayesian approach integrating regional and global features for image semantic learning
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
A Retrieval Method of Similar Strings Using Substrings
ICCEA '10 Proceedings of the 2010 Second International Conference on Computer Engineering and Applications - Volume 02
Text Segments as Constrained Formal Concepts
SYNASC '10 Proceedings of the 2010 12th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing
Image annotation by incorporating word correlations into multi-class SVM
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Recent progress in natural computation and knowledge discovery
A behavioural mode research on user-focus summarization
Mathematical and Computer Modelling: An International Journal
Hi-index | 0.00 |
Traditional CBIR method relies on visual features to identify objects in an image and uses predefined terms to annotate images, thus it fails to depict the implicit meanings. Recent textual content analysis methods applied to image annotation were blamed for their complexity of computation. In this research, we propose a corpus-free, relatively light computation of term segmentation method, namely "Iterative Merging Chinese Segmentation (IMCS) ," to identify representative terms from a single web page to obtain anecdotes as a semantic enrichment of the target image. It requires minimum computation needs that allows to share characters/words and facilitate their use at fine granularities without prohibitive cost. In the experiment, this method achieves a precision rate of 86.02%, and gains acceptance from expert rating and user rating of 75% and 68%, respectively. In performance testing, it only takes 0.006 second to process each image in a collection of 1,728 testing data set.