ckermorvant.bsky.social
@ckermorvant.bsky.social
...va attirer l'attention de la préfecture de police sur lui. Contraint de prouver ses origines, il se lance dans une enquête sur « Mr Klein », son double et ses racines familiales, en Alsace, à Marseille, à Alger et en Hollande. Un excellent film, à voir ou revoir
February 17, 2025 at 7:48 AM
Le personnage de Mr Klein est un marchand d'art qui, sous l'Occupation, profite des juifs contraints de vendre leurs biens, insouciant et indifférent à la politique qui se joue autour de lui. Mais un gain de sable dans la machine administrative du fichage des juifs...
MONSIEUR KLEIN de Joseph Losey - Official trailer - 1976
YouTube video by FURY
www.youtube.com
February 17, 2025 at 7:48 AM
I will be presenting how #Arkindex is being used to scale document processing to industrial scale for the #socface project @pse.bsky.social #INED #ArchivesNationales
December 19, 2024 at 9:13 AM
This presentation was an opportunity to introduce the hikaria.org website, the first version of a tool for exploring the @museeguimet.bsky.social 's collection of early Japanese photographs.
December 13, 2024 at 11:45 AM
Second day in Marburg : Erik Radisch from Sächsischen Akademie der Wissenschaften presents an integration of #SegmentAnything into #Annotorious
December 13, 2024 at 9:27 AM
A fascinating presentation by Ralph Ewert, Leibniz University Hannover: Unlocking Cultural Heritage: Computer Vision for Art and History Archives with the platform iART with semantic search, geoestimation, iconclass, pose estimation, date estimation www.iart.vision
iART
An Interactive Analysis and Retrieval Tool to Support Image-Oriented Research Processes
www.iart.vision
December 12, 2024 at 4:34 PM
Frank Puppe presents a Pipeline for Digital Indexing of Archaeological Record Card. Does ChatGPT solve the problem of textual information extraction in historical documents ? Results are often superior to previous methods, but new problems arise such as incompleteness and hallucinations.
December 12, 2024 at 2:28 PM
Nice experiments by Günther Mühlberger @uniinnsbruck.bsky.social , collaborating with a popular LLM for textual and image historical documents exploration. LLM doesn't deign to do full transcription (it calls tesseract) : HTR is still necessary, especially for historical documents.
December 12, 2024 at 1:32 PM
First presentation by Taylor Arnold @urichmond.bsky.social
: Explainable and Auditable Search and Discovery of Visual Cultural Heritage Collections. Very inspiring overview of metadata, machine learning, deep learning, vLLMs for distant viewing @distantviewinglab.bsky.social
December 12, 2024 at 12:50 PM