Multi-graph multi-instance learning for object-based image and video retrieval
Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
A method for detecting salient regions using integrated features
Proceedings of the 20th ACM international conference on Multimedia
SIFT match verification by geometric coding for large-scale partial-duplicate web image search
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Image annotation by semi-supervised cross-domain learning with group sparsity
Journal of Visual Communication and Image Representation
Visual attention modeling based on short-term environmental adaption
Journal of Visual Communication and Image Representation
Accurate off-line query expansion for large-scale mobile visual search
Signal Processing
MLRank: Multi-correlation Learning to Rank for image annotation
Pattern Recognition
Personalized image recommendation and retrieval via latent SVM based model
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Information Sciences: an International Journal
Hybrid image summarization by hypergraph partition
Neurocomputing
Learning to Recommend Descriptive Tags for Questions in Social Forums
ACM Transactions on Information Systems (TOIS)
Support vector description of clusters for content-based image annotation
Pattern Recognition
Hi-index | 0.00 |
In most of the learning-based image annotation approaches, images are represented using multiple-instance (local) or single-instance (global) features. Their performances, however, are mixed as for certain concepts, the single-instance representations of images are more suitable, while for others, the multiple-instance representations are better. Thus this paper explores a unified learning framework that combines the multiple-instance and single-instance representations for image annotation. More specifically, we propose an integrated graph-based semi-supervised learning framework to utilize these two types of representations simultaneously. We further explore three strategies to convert from multiple-instance representation into a single-instance one. Experiments conducted on the COREL image dataset demonstrate the effectiveness and efficiency of the proposed integrated framework and the conversion strategies.