Knowledge about the presence of people in a video is a valuable source of information in many applications, such as video annotation, retrieval and summarisation. The contribution of this paper goes in the direction of demonstrating how AI-based face processing technologies can be profitably used to perform video annotation of television content. To validate our vision, we developed the Face Management Framework (FMF), which implements an end-to-end pipeline for face analysis and content annotation based on few-shot or zero-shot face embedding extraction models. The results of the test campaign of the system show that the key performance indicators that we defined were exceeded by a wide margin, demonstrating how media workflows could greatly benefit from the tool and the efficiency improvements it brings.

Timeline summarization aims at presenting long news stories in a compact manner. State-of-the-art approaches first select the most relevant dates from the original event timeline then produce per-date news summaries. Date selection is driven by either per-date news content or date-level references. When coping with complex event data, characterized by inherent news flow redundancy, this pipeline may encounter relevant issues in both date selection and summarization due to a limited use of news content in date selection and no use of high-level temporal references (e.g., the past month). This paper proposes a paradigm shift in timeline summarization aimed at overcoming the above issues. It presents a new approach, namely Summarize Date First, which focuses on first generating date-level summaries then selecting the most relevant dates on top of summarized knowledge. In the latter stage, it performs date aggregations to consider high-level temporal references as well. The proposed pipeline also supports frequent incremental timeline updates more efficiently than previous approaches. We tested our unsupervised approach both on existing benchmark datasets and on a newly proposed benchmark dataset describing the COVID-19 news timeline. The achieved results were superior to state-of-the-art unsupervised methods and competitive against supervised ones.

This paper describes AgileRAI, a framework for searching, organising and accessing multimedia data in a fast and semantic-driven way. AgileRAI supports real time ingestion of video streams on which different machine learning techniques (such as global and local visual features extraction and matching) are applied in a parallel and scalable way. Extracted features are matched to a reference database of visual patterns (e.g. buildings, paintings, monuments) in order to produce a set of meta-tags describing the ingested contents. Furthermore, these tags are semantically enriched using open semantic data repositories. The system is designed with a scale-out pattern architecture based on Apache Spark, ensuring high-performance in Big Data management environments.

This demo paper describes a system for contextual advertising on aggregations of multimodal news items. The prototype is intended to demonstrate how modern content analysis techniques can be profitably used to automate tasks commonly performed by humans such as the planning of the computer-assisted advertising content.

Despite the number of efforts, managing content for media production and distribution can be still considered a time-consuming and hard task. From here derives the need for effective data documentation and retrieval systems. Hyper Media News provides a set of integrated tools for large-scale acquisition, analysis, indexing, browsing and recommendation of news content from both television and the Web.

Current Web technology has enabled the distribution of informative content through dynamic media platforms.In addition, the availability of the same content in the form of digital multimedia data has dramatically increased.Content-based, cross-media retrieval applications are needed to efficiently access desired information from this variety of data sources. This paper presents a novel approach for cross-media information aggregation, and describes a prototype system implementing this approach. The prototype adopts online newspaper articles and TV newscasts as information sources, to deliver a service made up of items including both contributions. Extensive experiments prove the effectiveness of the proposed approach in a real-world business context.

The quantity of multimedia content available either through the traditional distribution channels, such as broadcast television, or through new platforms like the Internet, is continuously increasing. Tools for user-oriented access to desired information are thus needed. In this paper, we illustrate a novel fuzzy multimedia mining technique for genre characterisation, aimed at overcoming limitations of conventional crisp classification systems. Effective results in genre classification and characterisation are presented based on the extraction of structural and cognitive properties of the content.