Abstract. The location of video scenes is an important semantic descriptor especially for broadcast news video. In this paper, we propose a learning-based approach to annotate shot...
— The use of digital learning resources creates an increasing need for semantic metadata, describing the whole resource, as well as parts of resources. Traditionally, schemas suc...
We present a system that learns to follow navigational natural language directions. Where traditional models learn from linguistic annotation or word distributions, our approach i...
Maintaining high annotation consistency in large corpora is crucial for statistical learning; however, such work is hard, especially for tasks containing semantic elements. This p...
Dance is the real cultural wealth of any nation and dance media is the source for learning the dance steps by the present and future generation of students. Dance videos exhibit r...