Multimedia Classification and Retrieval

Classification of multi-label data

PRA Lab is working on methods for attaining a trade-off between manual annotation effort and accuracy of automatic annotation and on techniques for multi-label classification, which is the task of deciding which labels, among a predefined set, can better describe the content of a given document/image.


Content-based image retrieval

The volume of multimedia content is increasing at a fast space due to the widespread availability of portable devices for the acquisition of images and videos. PRA Lab is working on advanced tools for managing such a large volume of data for the efficient retrieval of multimedia content related to a specific concept.