Near future
No Result
View All Result
December 5 2023
  • Home
  • Tech
  • Healthcare
  • Ambiente
  • Energy
  • Transports
  • Spazio
  • AI
  • concepts
  • H+
News about the world of tomorrow.
CES2023 / Coronavirus / Russia-Ukraine
Near future
  • Home
  • Tech
  • Healthcare
  • Ambiente
  • Energy
  • Transports
  • Spazio
  • AI
  • concepts
  • H+

News about the world of tomorrow.

No Result
View All Result
Technology

Here's an AI that can predict the next 25 frames of a movie

An artificial intelligence is able to predict quite accurately what the 25 future frames of this movie will be.

November 8, 2019
Gianluca RiccioGianluca Riccio
⚪ 3 minutes
Share15Pin2Tweet7SendShare2ShareShare1

Follow the Futuro Prossimo Whatsapp Channel! Daily updates and extra content.

Sign up for free

AI and machine learning algorithms are getting better at predicting actions in videos.

The best of current algorithms can predict quite precisely where a baseball will go after it has been thrown, or the appearance of a road in the sequence to come. In other words? Predicting frames in the future of a movie.

A new approach proposed by researchers at Google, University of Michigan and Adobe advances the state of the art with large-scale models that generate high-quality video from a few frames.

"With this project we aim to obtain precise video predictions. We will optimize the capabilities of a neural network", the researchers wrote in a document which describes their work.

The team model

The team's core model is based on a stochastic video generation architecture, with a component that manages the predictions of the frames following those considered.

The article continues after the related links

End of humanity, the 14 traps that no one dares face

Immersed in the future: how AI and VR will redefine our physical reality

The team trained and tested different versions of the model separately from custom datasets based on three forecast categories: interactions between objects, structured movement and partial observability.

For the first task (interactions with objects) the researchers selected 256 clips from a block of videos showing a robotic arm while interacting with towels.

For the second (structured movement) they edited clips from Human 3.6M, a block containing clips of humans performing actions like sitting in a chair.

As for the third (partial observability activity), used an open source KITTI driving dataset collected from footage of cameras mounted on car dashboards.

After this "training," the AI ​​model generated up to 25 frames in the future.

Researchers report that "predictions" were preferred 90,2, 98,7%, and 99,3% of the time by evaluators to the three types of video, respectively: object interactions, structured motion, and partial observability tasks. respectively.

Qualitatively, the team notes that the AI ​​has crisply represented human arms and legs and done "very accurate predictions that seemed realistic compared to the scenes depicted in the video" .

The artificial intelligence model while providing video data frames of human actions
The artificial intelligence model while providing video data frames of a car camera.

"We found that maximizing the capacity of such models improves the quality of the video prediction," coauthors write. We hope our work will encourage the field to move in similar directions in the future. For example to see how far we can go ".

How many minutes of the future can you imagine?

Tags: AIForecastsVideo


GPT Chat Megaeasy!

Concrete guide for those approaching this artificial intelligence tool, also designed for the school world: many examples of applications, usage indications and ready-to-use instructions for training and interrogating Chat GPT.

To submit articles, disclose the results of a research or scientific discoveries write to the editorial staff

Latest news

Power waves: transforming sea movement into energy for ships

Mind Uploading: putting your mind on a computer? For some it is possible

Forget everything: with Uni Wheel Hyundai reinvents the wheel

Granville T.Woods, the African-American genius that Edison tried to steal

Basic income in Kenya: surprising results from the global experiment

Small as an A4 sheet: The crazy Arma electric scooter

Traumatic brain injuries, EyeD can save your life in minutes

Cerabyte, the incredible ceramic memory: 10.000TB in one hand

The "dream" of robotic pizza fails: half a billion dollar collapse

No-Kids, more and more people choose life without children (and regrets)

The EU is making a big push for the cleanest energy in the world

Prophetic, the startup that wants to make us work even in our sleep

Follow us on the Futuroprossimo channels! We're up Telegram, Whatsapp, Instagram, Facebook, Twitter, Mastodon, Analysis.

FacebookTwitterInstagramTelegramAnalysisMastodonPinterestTikTok

The daily tomorrow.


Futuroprossimo.it provides news on the future of technology, science and innovation: if there is something that is about to arrive, here it has already arrived. FuturoProssimo is part of the network ForwardTo, studies and skills for future scenarios.

  • Ambiente
  • Architecture
  • Artificial intelligence
  • Gadgets
  • concepts
  • Design
  • Medicine
  • Spazio
  • Robotica
  • Work
  • Transports
  • Energy
  • Edition Francaise
  • Deutsche Ausgabe
  • Japanese version
  • English Edition
  • Portuguese Edition
  • Read more
  • Spanish edition

Subscribe to our newsletter

  • The Editor
  • Advertising on FP
  • Privacy Policy

© 2023 Near future - Creative Commons License
This work is distributed under license Creative Commons Attribution 4.0 International.

No Result
View All Result
News about the world of tomorrow.
  • Home
  • Tech
  • Healthcare
  • Ambiente
  • Energy
  • Transports
  • Spazio
  • AI
  • concepts
  • H+