Music genre classification techniques are typically applied to the data matrix whose columns are the feature vectors extracted from music recordings. In this paper, a feature vecto...
Classifying materials from their appearance is a challenging problem, especially if illumination and pose conditions are permitted to change: highlights and shadows caused by 3D st...
Eric Hayman, Barbara Caputo, Mario Fritz, Jan-Olof...
We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned obje...
Abstract. Bag-of-features representations have recently become popular for content based image classification owing to their simplicity and good performance. They evolved from text...
Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...