Content-Based Image Retrieval Using Multiple-Instance Learning
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Multiple-Instance Learning for Natural Scene Classification
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Multi-level annotation of natural scenes using dominant image components and semantic concepts
Proceedings of the 12th annual ACM international conference on Multimedia
Learning Multiple Tasks with Kernel Methods
The Journal of Machine Learning Research
Large Margin Methods for Structured and Interdependent Output Variables
The Journal of Machine Learning Research
International Journal of Computer Vision
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
MILES: Multiple-Instance Learning via Embedded Instance Selection
IEEE Transactions on Pattern Analysis and Machine Intelligence
An adaptive graph model for automatic image annotation
MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval
Working Set Selection Using Second Order Information for Training Support Vector Machines
The Journal of Machine Learning Research
Correlative multi-label video annotation
Proceedings of the 15th international conference on Multimedia
Cutting-plane training of structural SVMs
Machine Learning
Correlative linear neighborhood propagation for video annotation
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Sharing features: efficient boosting procedures for multiclass object detection
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
IEEE Transactions on Image Processing
Automatic image tagging through information propagation in a query log based graph structure
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Personalizing automated image annotation using cross-entropy
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Tag suggestion and localization for web videos by bipartite graph matching
WSM '11 Proceedings of the 3rd ACM SIGMM international workshop on Social media
Image tagging by exploiting feature correlation
ICADL'11 Proceedings of the 13th international conference on Asia-pacific digital libraries: for cultural heritage, knowledge dissemination, and future creation
Multi-modal region selection approach for training object detectors
Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
Assistive tagging: A survey of multimedia tagging with human-computer joint exploration
ACM Computing Surveys (CSUR)
Label-to-region with continuity-biased bi-layer sparsity priors
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Improving image tags by exploiting web search results
Multimedia Tools and Applications
Multimedia information retrieval on the social web
Proceedings of the 22nd international conference on World Wide Web companion
Using tagged images of low visual ambiguity to boost the learning efficiency of object detectors
Proceedings of the 21st ACM international conference on Multimedia
Collaborative topic regression with social regularization for tag recommendation
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Hi-index | 0.00 |
Large-scale loosely-tagged images (i.e., multiple object tags are given loosely at the image level) are available on Internet, and it is very attractive to leverage such loosely-tagged images for automatic image annotation applications. In this paper, a multi-task structured SVM algorithm is developed to leverage both the inter-object correlations and the loosely-tagged images for achieving more effective training of a large number of inter-related object classifiers. To leverage the loosely-tagged images for object classifier training, each loosely-tagged image is partitioned into a set of image instances (image regions) and a multiple instance learning algorithm is developed for instance label identification by automatically identifying the correspondences between multiple tags (given at the image level) and the image instances. An object correlation network is constructed for characterizing the inter-object correlations explicitly and identifying the inter-related learning tasks automatically. To enhance the discrimination power of a large number of inter-related object classifiers, a multi-task structured SVM algorithm is developed to model the inter-task relatedness more precisely and leverage the inter-object correlations for classifier training. Our experiments on a large number of inter-related object classes have provided very positive results.