We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Sequence matching techniques are effective for comparing two videos. However, existing approaches suffer from demanding computational costs and thus are not scalable for large-sca...
Semantic detection and recognition of objects and events contained in a video stream has to be performed in order to provide content-based annotation and retrieval of videos. This...
Lamberto Ballan, Marco Bertini, Alberto Del Bimbo,...
Motion2Sound is a program that translates motion properties into sound ones. This is done by using a motion detection system(Open Cv) and one can have as an input a live web-cam o...
Thermal infrared (IR) imagery offers a promising alternative to visible imagery for face recognition due to its relative insensitive to variations in face appearance caused by ill...
George Bebis, Aglika Gyaourova, Saurabh Singh, Ioa...