Abstract. We propose an online learning algorithm to tackle the problem of learning under limited computational resources in a teacher-student scenario, over multiple visual cues. ...
In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlatio...
In context photography, sensors gather real-time context information, which visually affects a photograph as it is taken. We have implemented a prototype running on standard camer...
The large-scale visual concept detection and annotation task (LS-VCDT) in ImageCLEF 2009 aims at the detection of 53 concepts in consumer photos. These concepts are structured in ...
Concept maps are an important tool to knowledge organization, representation, and sharing. Most current concept map tools do not provide full support for hand-drawn concept map cr...