Multimodal UI for Video Retrieval at the Swiss Federal Archives

The Swiss Federal Archives (SFA) is responsible for the archiving of the administrative records of the federal authorities, in particular the government, the parliament and the administration. Access to and the consultation of records by researchers and the public is a cornerstone of its legal mandate. In order to meet the current and future access requirements, the SFA is pursuing a strategy of consistent digital transformation aimed at facilitating access to archival information for users. The advent of digital technology and artificial intelligence (AI) has revolutionised methods and tools in this context. For several years, the SFA has been combining AI methods and their application to historical sources, such as the use of Automated Handwritten Text Recognition (AHTR) on the website Minutes of the Federal Council (1848-1972). In 2022, the SFA decided to implement Archipanion, a service provided by 4eyes and implemented on top of vitrivr, a content-based multimedia information retrieval system, to improve access to its digital film collection “Filmwochenschau (1940-1975)”. Formerly indexed using standard methods without direct content exploitation, the collection is now easily searchable through AI-driven, content-based processing. This technological advancement provides both users and scholars with unprecedented access to over 1,651 editions, facilitating research and exploration anytime and anywhere.

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2024-09-12
DOI
https://doi.org/10.5281/zenodo.13908128
Primary Topic
Video Analysis and Summarization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Multimodal UI for Video Retrieval at the Swiss Federal Archives

Zenodo (CERN European Organization for Nuclear Research)
Video Analysis and Summarization
article

Multimodal UI for Video Retrieval at the Swiss Federal Archives

article en

Abstract

The Swiss Federal Archives (SFA) is responsible for the archiving of the administrative records of the federal authorities, in particular the government, the parliament and the administration. Access to and the consultation of records by researchers and the public is a cornerstone of its legal mandate. In order to meet the current and future access requirements, the SFA is pursuing a strategy of consistent digital transformation aimed at facilitating access to archival information for users. The advent of digital technology and artificial intelligence (AI) has revolutionised methods and tools in this context. For several years, the SFA has been combining AI methods and their application to historical sources, such as the use of Automated Handwritten Text Recognition (AHTR) on the website Minutes of the Federal Council (1848-1972). In 2022, the SFA decided to implement Archipanion, a service provided by 4eyes and implemented on top of vitrivr, a content-based multimedia information retrieval system, to improve access to its digital film collection “Filmwochenschau (1940-1975)”. Formerly indexed using standard methods without direct content exploitation, the collection is now easily searchable through AI-driven, content-based processing. This technological advancement provides both users and scholars with unprecedented access to over 1,651 editions, facilitating research and exploration anytime and anywhere.

Zenodo (CERN European Organization for Nuclear Research)
Swiss Federal Archives (CH)
Openalex Percentile: Top 67%
Video Analysis and Summarization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Multimodal UI for Video Retrieval at the Swiss Federal Archives · Zenodo (CERN European Organization for Nuclear Research) (2024) | TGRS Research Map | TGRS