In this paper we describe our TRECVID 2007 experiments. The MediaMill team participated in two tasks: concept detection and search. For concept detection we extract regionbased im...
Cees G. M. Snoek, I. Everts, Jan van Gemert, Jan-M...
Scenes lit with high dynamic range environment maps of real-world environments exhibit all the complex nuances of natural illumination. For applications that need lighting adjustm...
Interactive montage combines the elements of play and visual representation. The analysis of four examples of interactive montage in reference to a first person point of view high...
Audio-visual speaker diarisation is the task of estimating “who spoke when” using audio and visual cues. In this paper we propose the combination of an audio diarisation syste...
Abstract. In this paper we examine whether the student-to-tutor convergence of lexical and speech features is a useful predictor of learning in a corpus of spoken tutorial dialogs....