FIAT/IFTA World Conference 2026

In the high-pressure environment of major broadcasting, the demand for archival media is defined by speed, precision, and instant availability. At Globo, managing decades of rich audiovisual heritage across Journalism, Sports, and Entertainment requires a constant evolution of archival strategies. The Globo Mídia project represents the latest strategic leap in this journey, designed to amplify the reach and agility of our media ecosystem through advanced data structures.


The core of Globo Mídia lies in the implementation of ontologies that structure vast amounts of media data, providing a unified semantic language across the company. This framework provides the necessary context for AI-driven initiatives, ensuring that technology acts as a powerful ally in metadata extraction and information retrieval. By creating these intelligent connections, Globo Mídia ensures high-speed discovery and accuracy, even in the most demanding and time-sensitive production scenarios.


The ultimate goal of this technological advancement is to liberate the researcher’s eye. By using the Globo Mídia ecosystem to automate mechanical indexing and repetitive tagging, we empower our specialists to transcend labor-intensive tasks. This shift allows the human researcher to focus entirely on their role as a strategic content partner and curator, applying historical sensitivity and deep creative insight to the development of new products.


At Globo, we believe that technology should handle the scale and complexity of the data so that human intelligence can drive the storytelling. We will demonstrate how Globo Mídia bridges the gap between massive archival collections and high-demand production needs, ensuring that our historical assets are instantly accessible to fuel future creativity and narrative excellence.

This presentation will reflect on the full trajectory from data preparation to public launch, culminating in the go-live of the Treasury Chamber mid 2026. We will share initial user responses and usage patterns, examining whether they aligned with expectations formed during development or revealed unforeseen behaviors and needs. In doing so, we aim to provide insight into how large-scale data transformation, ethical decision-making, and real-world user engagement intersect in the creation of a cultural heritage platform.
2 years ago in Bucharest, Sound & Vision presented its preparations for the mass-scale publication of audiovisual collections, supported in part by the EU Copyright Directive and its provisions for making out-of-commerce works accessible online. At that stage, the focus lay primarily on large-scale data processing: analyzing metadata quality, streamlining rights information, and implementing workflows to support sustainable data management and clearance activities.
In the past years, this preparatory work evolved into a series of concrete decisions about how data should be transformed, enriched, and ultimately presented to end users. This included choices about metadata normalization, contextual enrichment, and the balance between completeness and usability in the user interface. Particular attention was paid to how archival data—often complex, inconsistent, or incomplete—could be made accessible and meaningful without oversimplifying its context.
Alongside these technical and design considerations, ethical questions played a role. Decisions had to be made about what material could and should be published online, how to handle sensitive or potentially problematic content, and how to responsibly represent historical records in a public-facing environment. These considerations influenced not only rights clearance workflows but also data presentation strategies and access conditions within the platform.
To support collaboration between Sound & Vision and its external development partner, user archetypes were used to align discussions around user needs and expectations. However, also a very driver of development remained the data itself: its structure, limitations, and potential for reuse.

Many waves in technology development are stories of powerful entities becoming more powerful.  However, our work with audiovisual archives aims technology development along an alternative trajectory: rather than reinforcing the global monoculture, preserving the diversity of human experience and reducing the risk that less that less visible communities are absent from the historical record.


In this presentation, we describe work that follows this alternative trajectory to address such “archival absences". First, we introduce the CLAMS platform for computational processing of audiovisual archives. CLAMS is an open-source software designed to operate on modest, local hardware, permitting data sovereignty. With this computational context, we present two case studies from the collaboration between archivists at the American Archive of Public Broadcasting and researchers at Brandeis University on using technology to repair archival absences.  


The first case study focuses on cataloging items in broadcast television archives, demonstrating a multi-stage AI processing pipeline used by archivists to surface lesser-known individuals who appeared in old broadcast television programs in order to enrich metadata and improve discoverability.


The second case study focuses on linguistic absence and diversity. While ASR systems such as Whisper yield high quality transcripts of speech in high-resource languages, these systems offer no benefit for the unsupported languages and even produce misleading and nonsensical outputs. We present ongoing work on language identification for multilingual broadcast content, focusing on indigenous languages such as Yupik and Samoan. This includes challenges in segmentation, annotation, and evaluation, as well as the design of annotation workflows in collaboration with community experts.
These case studies illustrate how computational tools, when designed in collaboration with archivists and communities, can support more inclusive and representative audiovisual archives.  We close the presentation with an invitation to consider other sources of archival absence that can be resisted through creative collaborations between archivists and AI.

TVN holds one of the most significant archives in Latin America, preserving the social, political, and cultural heritage of our country through audiovisual records of incalculable value. This archive represents an emblematic case of the destruction of a large part of its collection following the Military Coup in Chile on September 11, 1973. Over the years, it has been recovered and is recognized today for the preserved content that has largely allowed us to reclaim our history as a society and a nation during those years.


Television material (news and programs) kept in the TVN Audiovisual Archive and produced during the Popular Unity government (Salvador Allende) was ordered to be eliminated—including the footage of Pablo Neruda receiving the Nobel Prize in Literature in 1971. However, with a sense of historical protection, these materials were hidden for years until Chile returned to democracy. Their preservation was a risky method during years dominated by institutional violence and uncertainty. Today, we can feel proud and fulfilled in our duty as "guardians of history and memory," because this content has been a fundamental pillar for countless historical recovery programs. These programs have allowed us to recognize ourselves as Chileans, to know who we were and what our society was like before the Military Dictatorship—how cities, inhabitants, urban tribes, and music have changed.


During difficult times, one way to protect the archive content marked for elimination was to remove the cards from the manual catalog that detailed the material. We created minimal descriptions of images documenting protests against Augusto Pinochet’s dictatorial regime in the 1980s. The cataloging systems for this new material were insufficient, or their context had been lost. It was a slow and costly task, making it difficult to reconstruct the moments they were recorded. We had to conduct extensive research to re-catalog this material, searching through newspapers and frequently consulting the memory of journalists for accurate descriptions. It was only then—at a time when it was finally possible to speak of human rights, political violence, or detained-disappeared persons—that we truly grasped the importance of having preserved those images. This process was necessary to establish how events unfolded in accordance with history.
The digitization process of this Archive began in 2010 with a planned ingestion project tailored to our needs and our commitment to the social role of the archive, which is part of the Audiovisual Heritage of TVN, Chile's public television.
It is important to highlight the work of librarians and journalists in re-cataloging content from those dictatorial times, when language was tightly controlled, and beginning to use a new language that accurately described what the images showed regarding Human Rights, violence, repression, and detained-disappeared persons.
With the help of digitization, we have set the fundamental task of increasing data collection to improve user-centered planning for this archive. We continue to move forward with the ingestion of historical content, solving daily the challenges posed by such old materials and formats that are increasingly difficult to rescue, but which contain valuable content reflecting the lives of Chileans during a specific era.


The commitment the Archive assumes toward history and the collective memory of a country is remarkable: without archives, there is no memory, and when we speak of memory, we are speaking of preservation.


Our mission as the Archive of Chilean Public Television is to preserve the audiovisual heritage that belongs to all Chileans. It is within this mission that we have focused our work to fulfill the challenge and dream of making the content archived and preserved for over 55 years available to all of Chilean society.


Finally, I believe that a great "vision for the future" will mark our path as archivists, allowing us to fulfill our mission of preserving images as a reflection of our society's history, ensuring that through them, memory can reconstruct the life lived.

As Ireland’s national public service media organisation, RTÉ holds a vast, irreplaceable repository of the state’s audiovisual heritage. However, the transition from physical carriers to a resilient digital future presents a challenge. This presentation examines RTÉ’s large-scale migration and digital preservation odyssey - a programme that balances the weight of historical stewardship with the realities of modern fiscal and technological constraints. We analyse the answers to key questions for this programme of projects, such as:

• How did we migrate different archive collections? i.e., how were resourcing challenges tackled and how did we decide on in-house versus outsourced aspects of migration?
• How did we restructure the archive department to accommodate the resourcing of the large-scale projects running in parallel to business as usual?
• How did RTÉ Technology approach this challenge, and what was the modern, resilient, and most cost-effective technology solution deployed to accommodate this mass migration and provide long-term digital access to audiovisual archive content?
• How did we introduce digital preservation principles, and what remains to be done in this area?

This presentation proposes a case study of data.ina.fr, a public platform developed by INA to unlock the potential of audiovisual archives by transforming them into long-term, interpretable data about media coverage in France. Rather than focusing on individual archive items or editorial reuse, data.ina.fr introduces a new paradigm: archives as a source of structured evidence that allows society to observe, compare, and understand media narratives over time. 
The platform analyses nearly two million hours of television and radio broadcasts from twenty French channels over a ten-year period (2015–2026). Through a set of interactive visualisations, it enables users to explore how current affairs are treated by media : which personalities dominate media attention, how territories are represented, how language evolves, and how gender balance in airtime varies across channels and years. This long-term, quantitative perspective put the spotlight on trends that are impossible to grasp through manual consultation of archives alone. 
data.ina.fr is grounded in two founding principles. First, to give meaning to archival collections beyond the archive object itself, by extracting indicators that allow comparison, verification, and contextualisation. Second, to create a tool for the objectivation of information over time, capable of supporting journalism, research, education, and public debate. In this sense, the project positions archives not only as heritage, but as a living public resource. 
This approach has made data.ina.fr a reference tool for professionals. Journalists from major national media regularly use the platform to support investigations, contextualise breaking news, and produce data-driven storytelling grounded in archival evidence. It is also integrated into journalism education, where it serves as a practical resource for teaching investigative methods based on quantitative analysis of media content. Beyond journalism, researchers in linguistics, political science, marketing, and public policy use the platform to analyse media representations and agenda-setting dynamics. 
Internally, data.ina.fr has transformed INA’s own editorial practices. Journalists rely on it to investigate issues such as gender-based violence, foreign interference campaigns, disinformation strategies, or media concentration. Monthly publications such as the data.ina.fr News Barometer provide recurring indicators on parity, territorial coverage, and dominant narratives, reinforcing INA’s role as a trusted public media actor capable of objectifying the media treatment of current affairs.