Filters








1 Hit in 0.047 sec

Structured max-margin learning for multi-label image annotation

Xiangyang Xue, Hangzai Luo, Jianping Fan
2010 Proceedings of the ACM International Conference on Image and Video Retrieval - CIVR '10  
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
more » ... arity 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, maxmargin 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.
doi:10.1145/1816041.1816056 dblp:conf/civr/XueLF10 fatcat:zmhoybpwo5drjlxi577nbyaawq