In this paper, we present a Question Answering system called KUQA (Korea University Question Answering system) developed by using semantic categories and co-occurrence density. Se...
Soo-Min Kim, Dae-Ho Baek, Sang-Beom Kim, Hae-Chang...
Conventional approaches to automatic image annotation usually suffer from two problems: (1) They cannot guarantee a good semantic coherence of the annotated words for each image, ...
Tao Mei, Yong Wang, Xian-Sheng Hua, Shaogang Gong,...
In this paper, we present a novel image representation that renders it possible to access natural scenes by local semantic description. Our work is motivated by the continuing effo...
Comprehensive coverage of the public web is crucial to web search engines. Search engines use crawlers to retrieve pages and then discover new ones by extracting the pages' o...
Organizing Web search results into a hierarchy of topics and subtopics facilitates browsing the collection and locating results of interest. In this paper, we propose a new hierar...