Text retrieval from broadcast news video is unsatisfactory, because a transcript word frequently does not directly ‘describe’ the shot when it was spoken. Extending the retriev...
We present Luminoso, a tool that helps researchers to visualize and understand a dimensionality-reduced semantic space by exploring it interactively. It also streamlines the proce...
Robert Speer, Catherine Havasi, K. Nichole Treadwa...
We present MikeTalk, a text-to-audiovisual speech synthesizer which converts input text into an audiovisual speech stream. MikeTalk is built using visemes, which are a set of imag...
Speeder Reader is an interactive reading station built around two primary ideas: dynamic text (especially RSVP, that is, rapid serial visual presentation), and the interface metap...
Maribeth Back, Jonathan Cohen, Steve R. Harrison, ...
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 ...