Skip to main content

This AI detects 11 types of emotions from a selfie


The machine learning models that can detect our face and movements are now part of our daily lives with smartphone features like face unlocking and Animoji. However, those AI models can’t predict how we feel by looking at our face. That’s where EmoNet comes in. Researchers from the University of Colorado and Duke University have developed the neural net that can accurately classify images in 11 emotional categories. To train the model, researchers used 2,187 videos that were clearly classified into 27 distinct emotion categories including anxiety, surprise, and sadness.  The team extracted 137,482 frames from these videos and then excluded sets of…

This story continues at The Next Web

from The Next Web https://ift.tt/2ypq536
Labels:

Comments

Post a Comment

Popular posts from this blog

TNW Podcast: Oscar Kneppers on academic startups; ESA wants to detect space-time ripples

Welcome to the new episode of the TNW Podcast — the show where we discuss the latest developments in the European technology ecosystem and feature interviews with some of the most interesting people in the industry. In today’s episode, Andrii and Linnea talk about a new European space mission, AI-generated podcasts, antiquated tech in German trains, and much more. In the interview section, we’re featuring a conversation with Oscar Kneppers, CEO of the Amsterdam Centre for Entrepreneurship, or ACE. He’s also founded several well-known local publications and one of the country’s major startup accelerators, Rockstart. Here are the stories and… This story continues at The Next Web from The Next Web https://ift.tt/a6AlDsr
Post a Comment
Read more

Swiss startup believes this forgotten element is the key to safe nuclear energy

Nuclear energy is undergoing a renaissance. Across Europe, governments are pouring huge amounts of money into new power plants while startups are busily working on smaller, modular alternatives.  Most of these plants rely on uranium, the radioactive metal that fuelled the atomic age (and contributed to a couple of catastrophic meltdowns). However, Swiss startup Transmutex wants to reinvent nuclear energy using a lesser-known element called thorium.  Uranium’s forgotten cousin Thorium is a lead-like metal that is mildly reactive, but four times more abundant than uranium and a lot safer to handle. However, thorium is a fissionable material but not a… This story continues at The Next Web from The Next Web https://ift.tt/ideQqVM
Post a Comment
Read more

Insta mules and crypto mixers: How tech is transforming money laundering

On the shallow surface of Instagram, Ramon “Hushpuppi” Abbas was a quintessential influencer. The flamboyant Nigerian portrayed a lavish lifestyle of private jets, luxury cars, and designer clothes. His glamorous adventures had earned him over 2 million followers and millions of dollars. But his posts concealed a darker reality. The 41-year-old was “one of the most prolific money launderers in the world,” according to the FBI. By his own admission, Hushpuppi conspired to launder over $300mn in just 18 months. One of his alleged clients was a certain Kim Jong Un — the supreme leader of North Korea. With his… This story continues at The Next Web from The Next Web https://ift.tt/rd549ui
Post a Comment
Read more