From a scientific/technical perspective, LiveMemories aimed at scaling up content extraction techniques towards very large scale extraction from multimedia sources, setting the scene for a Content Management Platform for Trentino; using this information to support new ways of linking, summarizing and classifying data in a new generation of digital memories which are `alive’ and user-centered; and to turn the creation of such memories into a communal web activity. Achieving these objectives made Trento a key player in the new Web Science Initiative, digital memories, and Web 2.0. But LiveMemories was also intended to have a social and cultural impact besides the scientific one: through the collection, analysis and preservation of digital memories of Trentino; by facilitating and encouraging the preservation of such community memories; and the fostering of new forms of community, and enrichment of our cultural and social heritage.
Weekly pick from the #MeetweenScientificWatch: “Video-SALMONN: Speech-enhanced audio-visual large language models” – Redefining video comprehension with speech-aware AV-LLMs and groundbreaking QA accuracy. 🎥🎤🤖
I’m glad to announce that our work “How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?” has been accepted at the Transactions of @aclanthology (TACL)! 🎉
The preprint is available here:
The new @iwslt shared task on instruction following speech models is out! Test sets will be available on the 1st of April and participants have to submit their models by April 15th. Check out the description for more info (or get in touch with us):
📢First Call for Papers 📢
The 22nd @iwslt event will be co-located with @aclmeeting
31 July-1 August 2025 –Vienna, Austria
Scientific submission due March 15, 2025
More details here:
@marcfede @esalesk @ELRAnews @shashwatup9k @MarineCarpuat @_janius_