I-Media-Cities, a searchable platform on moving images with automatic and manual annotations Simona Caraceni, Michele Carpenè, Mattia D'Antonio, Giuseppe Fiameni, Antonella Guidazzoli, Silvano Imboden, Maria Chiara Liguori, Margherita Montanari, Giuseppe Trotta and Gabriella Scipione Cineca, Italy Davy Hanegreefs Cinémathèque royale de Belgique, Bruxelles, Belgique davy.hanegreefs@cinematek.be Abstract— 9 European audiovisual archives provide access to their AV works, describing cities in all aspects from the end of the 19th century onwards, through the I-Media-Cities platform. The platform, with its dynamic processing pipeline and automatic video analysis tools, enables the enrichment of the moving images metadata in an innovative way, improving the “search and discovery” capabilities made available to researchers and citizens. Keywords— multimedia content, automatic and manual annotation, video analysis, 3D Web I. INTRODUCTION The I-Media-Cities project (IMC - http://imediacities.eu) is an ambitious initiative led by 9 European cultural institutions (film and audiovisual archives from 8 countries), 5 research institutions and 2 technological providers devised to enrich, share, provide access to and use digital content related to cities proposing it to researchers and the general public. A huge quantity of fictional and nonfictional AV works, describing cities in all aspects, including physical transformation and social dynamics from the end of the 19th century onwards, is the core content of the IMC e- environment, through which it is possible to collect, process, integrate and share this large collection of "moving images", via a metadata associated system. The three year project - at present at the end of its first year - is working on the development of the platform that is going to represent the underlying backbone of the whole project. The innovative aspect lies in the creation of a platform capable of performing a process of automatic annotation of multimedia contents, that have been already enriched with metadata and that will be further manually annotated. II. STATE OF THE ART Cultural, heritage and museum institutions across Europe are increasingly holding large digital collections – either digitized or born digital – that can have a significant impact on many research fields, both in Social Sciences and Humanities. This being a somehow recent development, a strong, efficient link between these institutions on the one hand and between them and the research field on the other still largely needs to be established, as well as a true bi-directional dialogue that aligns the efforts and the focus of these institutions to the needs of research. Equally important is the fact that neither cultural, heritage institutions nor the research field are taking full advantage of information technologies in order to improve the opportunities and the quality for research and for providing access to these collections. These two factors result in a general lack of significant research and experience in intelligent, technology-intensive, and user-engaging solutions (platforms, working environment, applications, etc.) designed to foster research on cultural digital collections across Europe. Furthermore, Film Heritage Institutions (FHI) apply many different standards and formats for both digital content and their metadata. Several recent developments to rectify this situation and to further collaboration notwithstanding, such as the publication of the ‘FIAF Moving Image Cataloguing Manual’ in 2016, exchange and reuse of digital cultural heritage content and metadata is still not a standard practice and remains complicated. Projects like IMC are therefore vital in creating user-friendly access to and interaction with content for a wide variety of users. They allow FHI’s to build bridges between European citizens and their own cultural heritage and stimulate re-use of this heritage for many different purposes, both inside and outside of the context of the archive. The IMC platform receives contents in the form of video, images, text and XML files with all the metadata provided by the audiovisual archives. Once the contents are uploaded inside the platform, several automatic images and video analysis tools, orchestrated through a pipeline, analyse them and extract information and metadata - at image, at frame or at shot level - that can be output in XML or in JSON. Cineca is the leading technological partner of IMC and the team involved in the project comes from the SuperComputing Applications and Innovation department (http://www.hpc.cineca.it/). One of the most challenging objectives that the HPC centers and hence Cineca are facing nowadays is to manage the data deluge coming from many