MIT AI Looks at Still Images, Predicts What Will Happen Next

...

The human brain's capacity for imagination is boundless. But machine intelligence still struggles to form images, ideas, and sensations without direct input.

Researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), however, led by PhD student Carl Vondrick, has developed a deep-learning algorithm that creates short videos to simulate the future of a still image, like a beach with crashing waves or golfers walking along the grass.

"These videos show us what computers think can happen in a scene," Vondrick said in a statement. "If you can predict the future, you must have understood something about the present."

Vondrick worked with MIT professor Antonio Torralba and University of Maryland Baltimore County professor Hamed Pirsiavash on the project. They are not the first to tackle this topic, but their model does pioneer new techniques—like processing an entire scene at once.

"Building up a scene frame-by-frame is like a big game of 'Telephone,' which means that the message falls apart by the time you go around the whole room," Vondrick said. "By instead trying to predict all frames simultaneously, it's as if you're talking to everyone in the room at once."

Using the "adversarial learning" method, the team trained two competing neural networks: one to generate video, the other to discriminate between what is real and what is fabricated. Over time, the generator learns to fool the discriminator, thus creating videos that resemble actual scenes from beaches, train stations, hospitals, and golf courses.

When put to the test, the algorithm generated videos that human subjects deemed realistic 20 percent more often than a baseline model.

But don't expect to see AI-conceived blockbusters on the big screen any time soon. The platform lacks some common sense, and is still too complex for anything longer than 1.5 seconds. Vondrick, however, has high hopes for the eventual production of longer-form videos.

"It's difficult to aggregate accurate information across long time periods in videos," he said. "If the video has both cooking and eating activities, you have to be able to link those two together to make sense of the scene."

According to MIT, this model could be used for adding animation to still images, detecting anomalies in security footage, and compressing data to store and send longer clips. "In the future, this will let us scale up vision systems to recognize objects and scenes without any supervision, simply by training them on video," Vondrick said.

Categories
GAMES
0 Comment

Leave a Reply

Captcha image


RELATED BY

  • 5300c769af79e

    Flexible Work Schedules: Key To Boosting Millennials' Productivity

    Driven by widespread access to high-speed wireless internet, portable mobile computing devices, and a generational shift in workplace attitudes, more workers are looking to adopt flexible work schedules, according to a FlexJobs survey of more than 3,000 respondents.The study found 51% of respondents prefer working at home when they need to get important work done, while others seek out co-working spaces, coffee shops, and libraries.
  • 5300c769af79e

    The Incident Response Success Checklist: Nine Critical Steps Your Current Plan Lacks

    Download Details matter when developing an incident response (IR) plan.But, even the most successful IR plans can lack critical steps, impeding how quickly normal business operations are restored.
  • 5300c769af79e

    6 Big Sales and Marketing Challenges Solved

    Many businesses are investing heavily in big data analytics, with much of that spending on predictive analytics technology that can analyze data to forecast future events.These solutions are particularly useful for sales and marketing teams, helping to create targeted campaigns and touches that increase sales.
  • 5300c769af79e

    Why 1 Billion iPhones Sold Matters

    You have manufacturers adding features that are for marketing -- not because they're necessary or desired," he said.Although the latest iPhone sales numbers show a year-over-year decline, that is likely to change.