Correlative multi-label multi-instance image annotation
Correlative multi-label multi-instance image annotation
复制标题
DOI：
10.1109/iccv.2011.6126300
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
X. Xue;Wei Zhang;Jie Zhang;Bin Wu;Jianping Fan;Yao Lu
中科院分区：
文献类型：
--
作者：
X. Xue;Wei Zhang;Jie Zhang;Bin Wu;Jianping Fan;Yao Lu
在本文中，每个图像被视为一个袋的局部区域，以及它是全球范围内调查。提出了一种新的多标签多实例图像标注方法，该方法同时获得图像级（袋级）标签和区域级（实例级）标签。语义概念和视觉特征之间的关联挖掘在图像级别和区域级别。标签间的相关性被捕获的概念对的共现矩阵。跨级别标签一致性对图像级别的标签与区域级别的标签之间的一致性进行编码。视觉特征和语义概念之间的关联，多个标签之间的相关性，以及跨级别的标签一致性充分利用，以提高标注性能。结构最大边缘技术被用来制定所提出的模型和多个相互关联的分类器联合学习。为了利用可用的图像级标记样本进行模型训练，首先通过建立多个袋级标签与图像区域之间的对应关系来完成训练集上的区域级标签识别。JEC距离为基础的内核被用来衡量图像之间和区域之间的相似性。在真实的图像数据集MSRC和Corel上的实验结果表明了该方法的有效性。
In this paper, each image is viewed as a bag of local regions, as well as it is investigated globally. A novel method is developed for achieving multi-label multi-instance image annotation, where image-level (bag-level) labels and region-level (instance-level) labels are both obtained. The associations between semantic concepts and visual features are mined both at the image level and at the region level. Inter-label correlations are captured by a co-occurence matrix of concept pairs. The cross-level label coherence encodes the consistency between the labels at the image level and the labels at the region level. The associations between visual features and semantic concepts, the correlations among the multiple labels, and the cross-level label coherence are sufficiently leveraged to improve annotation performance. Structural max-margin technique is used to formulate the proposed model and multiple interrelated classifiers are learned jointly. To leverage the available image-level labeled samples for the model training, the region-level label identification on the training set is firstly accomplished by building the correspondences between the multiple bag-level labels and the image regions. JEC distance based kernels are employed to measure the similarities both between images and between regions. Experimental results on real image datasets MSRC and Corel demonstrate the effectiveness of our method.