We are developing a testbed for learning by demonstration combining spoken language and sensor data in a natural real-world environment. Microsoft Kinect RGBDepth cameras allow us...
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. Different strategies to learn user semantic queries from dissimilarity representations of video audio-visual content are presented. When dealing with large corpora of vi...
Abstract. Query expansion has received extensive attention in information retrieval community. Although semantic based query expansion appears to be promising in improving retrieva...
The "Institut National de I'Audiovisuel" (1NA) is in charge of keeping records of national TV broadcasts. Its main function is to provide TV producers with authenti...
Marc Nanard, Jocelyne Nanard, David Genest, Michel...