• Home
  • About Us
  • Contact Us
  • Privacy Policy
  • Special Offers
Business Intelligence Info
  • Business Intelligence
    • BI News and Info
    • Big Data
    • Mobile and Cloud
    • Self-Service BI
  • CRM
    • CRM News and Info
    • InfusionSoft
    • Microsoft Dynamics CRM
    • NetSuite
    • OnContact
    • Salesforce
    • Workbooks
  • Data Mining
    • Pentaho
    • Sisense
    • Tableau
    • TIBCO Spotfire
  • Data Warehousing
    • DWH News and Info
    • IBM DB2
    • Microsoft SQL Server
    • Oracle
    • Teradata
  • Predictive Analytics
    • FICO
    • KNIME
    • Mathematica
    • Matlab
    • Minitab
    • RapidMiner
    • Revolution
    • SAP
    • SAS/SPSS
  • Humor

Researchers tout AI that can predict 25 video frames into the future

November 8, 2019   Big Data

AI and machine learning algorithms are becoming increasingly good at predicting next actions in videos. The very best can anticipate fairly accurately where a baseball might travel after it’s been pitched, or the appearance of a road miles from a starting position. To this end, a novel approach proposed by researchers at Google, the University of Michigan, and Adobe advances the state of the art with large-scale models that generate high-quality videos from only a few frames. All the more impressive, it does so without relying on techniques like optical flows (the pattern of apparent motion of objects, surfaces or edges in a scene) or landmarks, unlike previous methods.

“In this work, we investigate whether we can achieve high quality video predictions … by just maximizing the capacity of a standard neural network,” wrote the researchers in a preprint paper describing their work. “To the best of our knowledge, this work is the first to perform a thorough investigation on the effect of capacity increases for video prediction.”

The team’s baseline model builds on an existing stochastic video generation (SVG) architecture, with a component that models the inherent uncertainty in future predictions. They separately trained and tested several versions of the model against data sets tailored to three prediction categories: object interactions, structured motion, and partial observability. For the first task — object interactions — the researchers selected 256 videos from a corpus of videos of robot arm interacting with towels, and for the second — structured motion — they sourced clips from Human 3.6M, a corpus containing clips of humans performing actions like sitting on a chair. As for the partial observability task, they used the open source KITTI driving data set of front car dashboard camera footage.

 Researchers tout AI that can predict 25 video frames into the future

Above: The AI model predicts frames given videos from car dash cameras.

Team conditioned every model on between two input to five video frames and had the models predict between five to ten frames into the future during training, at a low resolution (64 by 64 pixels) for all tasks and at both a low and high resolution (128 by 128 pixels) for the objects interactions task  During testing, the models generated up to 25 frames.

The researchers report that one of the largest models was preferred 90.2, 98.7%, and 99.3% of the time by evaluators recruited through Amazon Mechanical Turk with respect to the object interactions, structured motion, and partial observability tasks, respectively. Qualitatively, the team notes that it crisply depicted human arms and legs and made “very sharp predictions that looked realistic in comparison to the ground truth.

 Researchers tout AI that can predict 25 video frames into the future

Above: The AI model predicts frames given videos of human activity.

“Our experiments confirm the importance of recurrent connections and modeling stochasticity [or randomness] in the presence of uncertainty (e.g., videos with unknown action or control),” wrote the paper’s coauthors. “We also find that maximizing the capacity of such models improves the quality of video prediction. We hope our work encourages the field to push along similar directions in the future – i.e., to see how far we can get … for achieving high quality video prediction.”

Let’s block ads! (Why?)

Big Data – VentureBeat

frames, future, into, predict, researchers, tout, VIDEO
  • Recent Posts

    • Building AI for the Global South
    • Dapper Duo
    • AI Weekly: These researchers are improving AI’s ability to understand different accents
    • Why Choose RapidMiner for Your Data Science & Machine Learning Software?
    • How to Use CRM Integration to Your Advantage – Real World Examples
  • Categories

  • Archives

    • March 2021
    • February 2021
    • January 2021
    • December 2020
    • November 2020
    • October 2020
    • September 2020
    • August 2020
    • July 2020
    • June 2020
    • May 2020
    • April 2020
    • March 2020
    • February 2020
    • January 2020
    • December 2019
    • November 2019
    • October 2019
    • September 2019
    • August 2019
    • July 2019
    • June 2019
    • May 2019
    • April 2019
    • March 2019
    • February 2019
    • January 2019
    • December 2018
    • November 2018
    • October 2018
    • September 2018
    • August 2018
    • July 2018
    • June 2018
    • May 2018
    • April 2018
    • March 2018
    • February 2018
    • January 2018
    • December 2017
    • November 2017
    • October 2017
    • September 2017
    • August 2017
    • July 2017
    • June 2017
    • May 2017
    • April 2017
    • March 2017
    • February 2017
    • January 2017
    • December 2016
    • November 2016
    • October 2016
    • September 2016
    • August 2016
    • July 2016
    • June 2016
    • May 2016
    • April 2016
    • March 2016
    • February 2016
    • January 2016
    • December 2015
    • November 2015
    • October 2015
    • September 2015
    • August 2015
    • July 2015
    • June 2015
    • May 2015
    • April 2015
    • March 2015
    • February 2015
    • January 2015
    • December 2014
    • November 2014
© 2021 Business Intelligence Info
Power BI Training | G Com Solutions Limited