The Community for Technology Leaders
2008 IEEE Conference on Computer Vision and Pattern Recognition (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
ISBN: 978-1-4244-2242-5
pp: 1-8
Zheng-Jun Zha , Department of Automation, University of Science and Technology of China, China
Xian-Sheng Hua , Internet Media Group, Microsoft Research Asia, China
Tao Mei , Internet Media Group, Microsoft Research Asia, China
Jingdong Wang , Internet Media Group, Microsoft Research Asia, China
Guo-Jun Qi , Department of Automation, University of Science and Technology of China, China
Zengfu Wang , Department of Automation, University of Science and Technology of China, China
ABSTRACT
In real world, an image is usually associated with multiple labels which are characterized by different regions in the image. Thus image classification is naturally posed as both a multi-label learning and multi-instance learning problem. Different from existing research which has considered these two problems separately, we propose an integrated multi-label multi-instance learning (MLMIL) approach based on hidden conditional random fields (HCRFs), which simultaneously captures both the connections between semantic labels and regions, and the correlations among the labels in a single formulation. We apply this MLMIL framework to image classification and report superior performance compared to key existing approaches over the MSR Cambridge (MSRC) and Corel data sets.
INDEX TERMS
CITATION

Zheng-Jun Zha, Guo-Jun Qi, Xian-Sheng Hua, Zengfu Wang, Jingdong Wang and Tao Mei, "Joint multi-label multi-instance learning for image classification," 2008 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Anchorage, AK, USA, 2008, pp. 1-8.
doi:10.1109/CVPR.2008.4587384
87 ms
(Ver 3.3 (11022016))