We present a holistic data-driven approach to image description generation, exploiting the vast amount of (noisy) parallel image data and associated natural language descriptions ...
Polina Kuznetsova, Vicente Ordonez, Alexander C. B...
In many practical applications, ontologies tend to be very large and complicated. In order for users to quickly understand and analyze large-scale ontologies, in this paper we prop...
Kewei Tu, Miao Xiong, Lei Zhang, Haiping Zhu, Jie ...
Latent semantic analysis (LSA), as one of the most popular unsupervised dimension reduction tools, has a wide range of applications in text mining and information retrieval. The k...
Xi Chen, Yanjun Qi, Bing Bai, Qihang Lin, Jaime G....
We present a novel, yet simple algorithm for clustering large collections of digital images. The method is applicable to consumer digital photo libraries, where it can be used to o...
In order to index Web images, the whole associated texts are partitioned into a sequence of text blocks, then the local relevance of a term to the corresponding image is calculated...