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: Boris comes over to co-host; Slack’s Cal Henderson talks European tech

 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 is joined by Boris Veldhuijzen van Zanten, co-founder, member of the board, and former CEO of TNW. The topics discussed include the jobs created by Dutch startups, giant state funding for energy projects, translations of the word ‘computer’, and a bunch of other things in between. In the interview section, we’re featuring a conversation with Cal Henderson, co-founder and… This story continues at The Next Web from The Next Web https://ift.tt/jUgcNFD
Post a Comment
Read more

NotJordanPeterson lets you generate uncannily realistic Jordan Peterson sound bites

Love him or hate him, Canadian psychologist Jordan Peterson has undeniably captivated the interest of supporters and critics alike, earning a reputation as a “rock star” academic – similarly to his colleague and debate rival Slavoj Zizek. Now he’s being replicated, by AI. While you can easily find hours of footage with Peterson, none of what you hear in this piece comes from his mouth. Instead, it’s been produced by a neural network – called NotJordanPeterson – which has been trained to mimic the voice of the psychologist. And the resemblance is… absolutely uncanny. Check out these examples we generated… This story continues at The Next Web from The Next Web https://ift.tt/306hAGA
Post a Comment
Read more

Partech raises $100M to back startups supporting new post-coronavirus reality

French venture capital firm Partech has raised a $100 million Seed fund to invest in post-COVID19 trends in health, work, commerce, finance, mobility, and computing. Partech, which has in the past backed UK data startup Privitar and French fintech company October, will be scouting the European, US, and Asian ecosystems. [Read: What’s venture capital and why does it matter for startups?] “While 3 billion people are confined at home, digitalization is bound to dramatically accelerate across sectors and ‘remote’ is emerging as a new standard,” reads the announcement post. “This redefines how people live, work and consume, while businesses have to… This story continues at The Next Web from The Next Web https://ift.tt/35cPpJ9
Post a Comment
Read more