Structured max-margin learning for multi-label image annotation

Authors:
Xiangyang Xue;Hangzai Luo;Jianping Fan
Affiliations:
Fudan University, Shanghai, China;East China Normal University, Shanghai, China;UNC-Charlotte, Charlotte, NC
Venue:
Proceedings of the ACM International Conference on Image and Video Retrieval
Year:
2010

Citing 14
Cited 3

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Learning Multiple Tasks with Kernel Methods

The Journal of Machine Learning Research
Learning Hierarchical Models of Scenes, Objects, and Parts

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Discriminative Random Fields

International Journal of Computer Vision
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

International Journal of Computer Vision
Representing shape with a spatial pyramid kernel

Proceedings of the 6th ACM international conference on Image and video retrieval
Correlative multi-label video annotation

Proceedings of the 15th international conference on Multimedia
LabelMe: A Database and Web-Based Tool for Image Annotation

International Journal of Computer Vision
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Flickr distance

MM '08 Proceedings of the 16th ACM international conference on Multimedia
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
Discriminative fields for modeling semantic concepts in video

Large Scale Semantic Access to Content (Text, Image, Video, and Sound)
Integrating Concept Ontology and Multitask Learning to Achieve More Effective Classifier Training for Multilevel Image Annotation

IEEE Transactions on Image Processing

Graph-based methods for the automatic annotation and retrieval of art prints

Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Multi-kernel multi-label learning with max-margin concept network

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Labelset anchored subspace ensemble (LASE) for multi-label annotation

Proceedings of the 2nd ACM International Conference on Multimedia Retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a structured max-margin learning scheme is developed to achieve more effective training of a large number of inter-related classifiers for multi-label image annotation. First, a visual concept network is constructed to characterize the inter-concept visual similarity contexts more precisely and determine the inter-related learning tasks automatically. Second, multiple base kernels are combined to achieve more precise characterization of the diverse visual similarity contexts between the images and address the issue of huge intra-concept visual diversity more effectively. Third, a structured max-margin learning algorithm is developed by incorporating the visual concept network, max-margin Markov networks and multi-task learning to address the issue of huge inter-concept visual similarity more effectively. Our structured max-margin learning algorithm can leverage the inter-concept visual similarity contexts to learn a large number of inter-related classifiers simultaneously and improve their discrimination power significantly. Our experiments have also obtained very positive results.