To help users organize and retrieve the image resources efficiently, most image sharing sites allow users to annotate the images with tags. Image tag recommendation systems aim to provide a set of tag candidates to facilitate the tagging process done by users. Previous image tag recommendation methods are usually developed based on tag co-occurrence information. However, due to the neglect of the visual information associated with images and the semantic diversity among recommended tags, the recommendation results of previous methods often suffer from the problems of tag ambiguity and redundancy. To solve the above problems, this paper proposes a novel image tag recommendation approach, which considers both the relevance and diversity of the recommended tags. First, the approach employs the visual language model to calculate the relevance between a tag and an image, as well as the visual distance between two tags. Then, according to the above calculations, a greedy search algorithm is proposed to find a tag set as the final recommendation, which reaches a reasonable trade-off between the relevance and diversity. Experiments on Flickr data set show the proposed approach outperforms the state-of-the-art methods in terms of precision, topic coverage and F1 value.%为了帮助用户高效地组织和检索图像资源,多数图像分享站点允许用户为图像添加标签.图像标签推荐系统旨在提供一组标签候选项来方便用户完成添加标签的过程.以往的图像标签推荐方法往往利用标签间的共现信息进行标签推荐.但是,由于忽略了图像的视觉内容信息和被推荐标签之间的多样性,以往方法的推荐结果常存在标签歧义和标签冗余的问题.为了解决上述问题,文中提出了一种新的图像标签推荐方法,该方法综合考虑了被推荐标签的相关性和多样性.首先,利用视觉语言模型,该方法分别计算标签与图像的相关性和标签之间的视觉距离.然后,基于上述计算,给出一个贪心搜索算法来找到能合理地平衡相关性和多样性的标签集合,将该集合作为最终的推荐.在Flickr数据集上的实验结果表明,该方法在准确率、主题覆盖率和F1测度上均优于目前的代表性方法.
展开▼
