jiajunhua的专栏

里面关于LDA的改进尤其值得一看，尤其后面的参考文献，北京邮电大学的博士论文 关键词抽取也有很多值得一看的地方

To address the second problem, wedevelop a Probabilistic Topic-Connection (PTC) model to represent the connection between latent semantic topic in text description and latent patterns from image feature space.We compare the performance of our model with the currently popularCorrespondence LDA (Corr-LDA) model under the same automatic image annotation scenario using cross-validation