Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Constrained K-means Clustering with Background Knowledge
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Automatic image annotation and retrieval using cross-media relevance models
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Journal of Machine Learning Research
Multi-level annotation of natural scenes using dominant image components and semantic concepts
Proceedings of the 12th annual ACM international conference on Multimedia
Effective automatic image annotation via a coherent language model and active learning
Proceedings of the 12th annual ACM international conference on Multimedia
WordNet: similarity - measuring the relatedness of concepts
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
CBSA: content-based soft annotation for multimodal image retrieval using Bayes point machines
IEEE Transactions on Circuits and Systems for Video Technology
A comparison of methods for multiclass support vector machines
IEEE Transactions on Neural Networks
Improving Automatic Image Annotation Based on Word Co-occurrence
Adaptive Multimedial Retrieval: Retrieval, User, and Semantics
Automatic Image Annotation Using Color K-Means Clustering
IVIC '09 Proceedings of the 1st International Visual Informatics Conference on Visual Informatics: Bridging Research and Practice
Automatic image annotation using a semi-supervised ensemble of classifiers
CIARP'07 Proceedings of the Congress on pattern recognition 12th Iberoamerican conference on Progress in pattern recognition, image analysis and applications
Image retrieval using Markov Random Fields and global image features
Proceedings of the ACM International Conference on Image and Video Retrieval
TSD'06 Proceedings of the 9th international conference on Text, Speech and Dialogue
Exploiting time in automatic image tagging
ECIR'13 Proceedings of the 35th European conference on Advances in Information Retrieval
| Hi-index | 0.00 |
Automatic image annotation concerns a process of automatically labeling image contents with a pre-defined set of keywords, which are regarded as descriptors of image high-level semantics, so as to enable semantic image retrieval via keywords. A serious problem in this task is the unsatisfactory annotation performance due to the semantic gap between the visual content and keywords. Targeting at this problem, we present a new approach that tries to incorporate lexical semantics into the image annotation process. In the phase of training, given a training set of images labeled with keywords, a basic visual vocabulary consisting of visual terms, extracted from the image to represent its content, and the associated keywords is generated at first, using K-means clustering combined with semantic constraints obtained from WordNet, then the statistical correlation between visual terms and keywords is modeled by a two-level hierarchical ensemble model composed of probabilistic SVM classifiers and a co-occurrence language model. In the phase of annotation, given an unlabeled image, the most likely associated keywords are predicted by the posterior probability of each keyword given each visual term at the first-level classifier ensemble, then the second-level language model is used to refine the annotation quality by word co-occurrence statistics derived from the annotated keywords in the training set of images. We carried out experiments on a medium-sized image collection from Corel Stock Photo CDs. The experimental results demonstrated that the annotation performance of this method outperforms some traditional annotation methods by about 7% in average precision, showing the feasibility and effectiveness of the proposed approach.