Past research on automatic laughter detection has focused mainly on audio-based detection. Here we present an audiovisual approach to distinguishing laughter from speech and we sh...
The Oxford/IIIT team participated in the high-level feature extraction and interactive search tasks. A vision only approach was used for both tasks, with no use of the text or aud...
XML data projection (or pruning) is one of the main optimization techniques recently adopted in the context of main-memory XML query-engines. The underlying idea is quite simple: ...
This paper describes a method for establishing dense correspondence between two images in a video sequence (motion) or in a stereo pair (disparity) in case of large displacements....
Moustapha Kardouchi, Janusz Konrad, Carlos V&aacut...
The extension of our research on analysis of a single agent or agent communities combining advanced methods of visualization with traditional AI techniques is presented in this pa...