We investigate methods of segmenting, visualizing, and indexing presentation videos by both audio and visual data. The audio track is segmented by speaker, and augmented with key ...
Abstract—Many important real-world systems, modeled naturally as complex networks, have heterogeneous interactions and complicated dependency structures. Link prediction in such ...
Darcy A. Davis, Ryan Lichtenwalter, Nitesh V. Chaw...
Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...
Site maps are frequently provided on Web sites as a navigation support for Web users. The automatic generation of site maps is a complex task since the structure of the data, sema...
Our research aims at interactive document viewers that can select and highlight relevant text passages on demand. Another related objective is the generation of topic-specific su...