Abstract: A technique for improving the performance of image classification systems is proposed which consists of learning an adaptation architecture on top of the input features jointly with linear classifiers, e.g., SVM. This adaptation method is agnostic to the type of input feature and applies either to features built using aggregators, e.g., BoW, FV, or to features obtained from the activations or outputs from DCNN layers. The adaptation architecture may be single (shallow) or multi-layered (deep). This technique achieves a higher performance compared to current state of the art classification systems.

Abstract: A method for identifying an object in a video archive including multiple images acquired in a network of cameras including a phase of characterization of the object to be identified and a phase of searching for the object in the archive, where the characterization phase consists of defining for the object at least one semantic characteristic capable of being extracted, even in low-resolution images, from the video archive.

Abstract: The invention concerns a method for identifying an object in a video archive including multiple images acquired in a network of cameras including a phase of characterisation of the object to be identified and a phase of searching for the said object in the said archive, where the said characterisation phase consists in defining for the said object at least one semantic characteristic capable of being extracted, even in low-resolution images, from the said video archive.