AI Dynamics

Global AI News Aggregator

MULTIMODAL AI

Translation Glasses App Test: Real-Time French Subtitles Experience

By

AI Dynamics

–

21 December 2022 0h18

Tested translation!

I’m wearing the glasses while the app is translating – it’s showing me the French subtitles as I speak.

Pros: fast, 9 languages, easy to use, easy to read in AR

Cons: have to specify “to and from” languages, lower accuracy when audio is hard (action movie) pic.twitter.com/6JWucXATkt
— Allie K. Miller (@alliekmiller) 20 décembre 2022

Tested translation! I’m wearing the glasses while the app is translating – it’s showing me the French subtitles as I speak. Pros: fast, 9 languages, easy to use, easy to read in AR Cons: have to specify “to and from” languages, lower accuracy when audio is hard (action movie)

→ View original post on X — @alliekmiller,

21 December 2022
Weekend Meme Sunday AI Computer Vision Humor Post

By

AI Dynamics

–

18 December 2022 4h12

The weekend is not the same without "Meme-orable" Sunday!
#memes #aimemes #AI #funny #computervision

→ View original post on X — @learnopencv,

18 December 2022
Computer Vision Improves Off-Side Rule Detection in Sports

By

AI Dynamics

–

17 December 2022 20h07

2/Human referees have struggled to accurately call violations of the off-side rule — a complex rule involving positions of multiple players and the ball. This is where computer vision steps in.

→ View original post on X — @andrewyng,

17 December 2022
Stable Diffusion Generates Music by Learning Images of Sheet Music

By

@swyx

–

15 December 2022 22h23

wait lol so turns out the solve to AI music generation wasnt novel approaches to learning the underlying structures of music

it was taking #StableDiffusion and finetuning for IMAGES OF MUSIC

and THAT WORKS?!?

synesthetes could never 🤯 https://t.co/zSfpFqsP3N pic.twitter.com/8gTbG5ZZuH
— swyx 🐣 (@swyx) 15 décembre 2022

wait lol so turns out the solve to AI music generation wasnt novel approaches to learning the underlying structures of music it was taking #StableDiffusion and finetuning for IMAGES OF MUSIC and THAT WORKS?!? synesthetes could never

→ View original post on X — @swyx,

15 December 2022
Harmonai joins Replicate with open source audio ML models

By

@replicate

–

15 December 2022 15h38

Also, welcome @harmonai_org to Replicate! They're a open source collective of audio ML hackers. This is just the first of many models they're working on and we're looking forward to all those robo-tunes.

→ View original post on X — @replicate,

15 December 2022
Thales Launches Multimodal Biometric Module for Facial and Iris Recognition

By

AI Dynamics

–

14 December 2022 12h48

The new multimodal biometric module from @thalesgroup combines facial and iris recognition https://actuia.com/actualite/le-nouveau-module-biometrique-multimodal-de-thales-combine-reconnaissance-faciale-et-de-liris/
… #AI #artificialintelligence #security

→ View original post on X — @actuiafr,

14 December 2022
Meta AI Unveils data2vec 2.0: 16x Faster Self-Supervised Learning

By

AI Dynamics

–

13 December 2022 16h01

Announcing data2vec 2.0, a new general self-supervised algorithm built by Meta AI for speech, vision & text that can train models 16x faster than the most popular existing algorithm for images while achieving the same accuracy. Read more & get the open source code

→ View original post on X — @aiatmeta,

13 December 2022
NVIDIA and Deutsche Bank Partnership: AI Innovation for Banking

By

AI Dynamics

–

07 December 2022 17h41

We announced details of a multi-year innovation partnership with @DeutscheBank
, including use cases across intelligent avatars, speech #AI, fraud detection, and risk management to reduce TCO up to 80%.

→ View original post on X — @nvidia,

7 December 2022
Stable Diffusion 2.0 launches on Replicate with enhanced capabilities

By

@replicate

–

06 December 2022 17h16

Stable Diffusion 2.0 is now on Replicate. It has a completely new text encoder developed by @laion_ai and can natively generate images at 768×768 pixels. https://
replicate.com/stability-ai/s
table-diffusion
…

→ View original post on X — @replicate,

6 December 2022
EDGE: AI-Generated Realistic Dances Synchronized with Music

By

AI Dynamics

–

05 December 2022 4h46

Found this interesting read. Imagine creating realistic, physically plausible dances that stay true to the music! This is made possible with EDGE – Editable Dance GEneration.
See it in action: https://t.co/bUfdQm5CDA
Paper: https://t.co/Byz1ik4qFw #github #arxiv #edge #ai pic.twitter.com/7ExZYdB1K6
— Satya Mallick (@LearnOpenCV) 5 décembre 2022

Found this interesting read. Imagine creating realistic, physically plausible dances that stay true to the music! This is made possible with EDGE – Editable Dance GEneration. See it in action: https://
edge-dance.github.io
Paper: https://
arxiv.org/abs/2211.10658 #github #arxiv #edge #ai

→ View original post on X — @learnopencv,

5 December 2022