Artificial Intelligence for Media and Humanities (AIMH)

Head: Giuseppe Amato


Web Site:

Artificial intelligence is changing our life in an unprecedented way and will have an impact on society comparable to the advent of the television, personal computers, and the world wide web. Artificial intelligence-enabled technology is increasingly becoming present in daily used devices and services like smartphones, smartwatches, smart tv sticks, personal computers, on-line shopping services, online entertainment services, on-line infotainment services.

The explosion of artificial intelligence, mostly driven by the advances in deep learning, has been significantly favored by the availability of powerful AI specialized hardware and very large datasets to be used to train AI algorithms. In fact, on one hand, GPU-powered devices allow processing huge amounts of training data in reasonable time. On the other hand, digital data produced by people, for instance with their smartphones, and shared on the world wide web and social networks, offer a valuable source of (noisily) annotated data that can be used to teach AI algorithms to perform a wide range of non-trivial tasks.

The Artificial Intelligence for Media and Humanities (AIMH) lab has the mission to investigate and advance the state of the art in the Artificial Intelligence field, specifically addressing applications to digital media and digital humanities, and taking also into account issues related to scalability.

Specifically, the AIMH lab pursues the following research lines:

AI and visual data: investigating new AI-based solutions to image and video content analysis, understanding, and classification. This includes techniques for detection, recognition (object, pedestrian, face, etc), classification, feature extraction (low- and high-level, relational, cross-media, etc), anomaly detection also considering adversarial machine learning threats.

AI and textual data: investigating AI-based solutions to textual data analysis, understanding, and classification. This includes representation learning for text classification, transfer learning for cross-lingual and cross-domain text classification, sentiment classification, sequence learning for information extraction, text quantification, transductive text classification, and applications of the above to domains such as authorship analysis and technology-assisted review.

AI and digital humanities: investigating AI-based solutions to represent, access, archive, and manage tangible and intangible cultural heritage data. This includes solutions based on ontologies, with a special focus on narratives, and solutions based on multimedia content analysis, recognition, and retrieval.

AI and large-scale multimedia information retrieval: investigating efficient, effective, and scalable AI-based solutions for searching multimedia content in large datasets of non-annotated data. This includes techniques for multimedia content extraction and representation, scalable access methods for similarity search, multimedia database management.