The Artificial Intelligence for Multimedia Information Retrieval (AIMIR) research group of the NeMIS-CNR lab has a long experience in topics related to

  • Artificial Intelligence
  • Multimedia Information Retrieval
  • Computer Vision
  • Similarity search on a large scale

We aim at investigating the use of Artificial Intelligence and Deep Learning, for Multimedia Information Retrieval, addressing both, issues of effectiveness and efficiency. Multimedia information retrieval techniques should be able to provide users with pertinent results, fast, on a huge amount of multimedia data.
Application areas of our research results range from cultural heritage to smart tourism, from security to smart cities, from mobile visual search to augmented reality.

[panel style=”panel-success”]
Our field of research

Artificial intelligence

We investigate techniques of machine learning and deep learning to build for instance visual classifiers, object recognition, and face recognition solutions. We also investigate biologically plausible neural network paradigms.

Multimedia Information Retrieval

MultiMedia Information Retrieval (MMIR) is a research discipline of computer science that aims at extracting semantic information from multimedia data sources. Data sources include directly perceivable media such as audio, image and video, indirectly perceivable sources such as text, biosignals as well as not perceivable sources such as bioinformation, stock prices, etc. To support the fast and effective retrieval of multimedia information on a huge amount of multimedia data we use the most advanced indexing techniques and metric access methods.

Computer Vision

Computer vision is a field that includes methods for acquiring, processing, analysing, and understanding images and, in general, high-dimensional data from the real world in order to produce numerical or symbolic information, e.g., in the forms of decisions.

Similarity Search

Current data processing applications use data with considerably less structure and much less precise queries than traditional database systems. Examples are multimedia data like images or videos that offer query by example search, product catalogs that provide users with reference-based search, scientific data records from observations or experimental analyses such as biochemical and medical data, or XML documents that come from heterogeneous data sources on the Web or in intranets and thus does not exhibit a global schema. Such data can neither be ordered in a canonical manner nor meaningfully searched by precise database queries that would return exact matches.
This novel situation is what has given rise to similarity searching, also referred to as content-based or similarity retrieval.