Automatic Photography with Google Clips

Automatic Photography with Google Clips

  • May 12, 2018
Table of Contents

Automatic Photography with Google Clips

How could we train an algorithm to recognize interesting moments? As with most machine learning problems, we started with a dataset. We created a dataset of thousands of videos in diverse scenarios where we imagined Clips being used.

We also made sure our dataset represented a wide range of ethnicities, genders, and ages. We then hired expert photographers and video editors to pore over this footage to select the best short video segments. These early curations gave us examples for our algorithms to emulate.

However, it is challenging to train an algorithm solely from the subjective selection of the curators — one needs a smooth gradient of labels to teach an algorithm to recognize the quality of content, ranging from ‘perfect’ to ‘terrible.’ To address this problem, we took a second data-collection approach, with the goal of creating a continuous quality score across the length of a video. We split each video into short segments (similar to the content Clips captures), randomly selected pairs of segments, and asked human raters to select the one they prefer.

Source: googleblog.com

Tags :
Share :
comments powered by Disqus

Related Posts

Artificial Neural Nets Grow Brainlike Navigation Cells

Artificial Neural Nets Grow Brainlike Navigation Cells

Having the sense to take a shortcut, the most direct route from point A to point B, doesn’t sound like a very impressive test of intelligence. Yet according to a new report appearing today in Nature, in which researchers describe the performance of their new navigational artificial intelligence, the system’s ability to explore complex simulated environments and find the shortest route to a goal put it in a class previously reserved for humans and other living things. The surprising key to the system’s performance was that while learning how to navigate, the neural net spontaneously developed the equivalent of “grid cells,” sets of brain cells that enable at least some mammals to track their location in space.

Read More
AI trained to navigate develops brain-like location tracking

AI trained to navigate develops brain-like location tracking

Now that DeepMind has solved Go, the company is applying DeepMind to navigation. Navigation relies on knowing where you are in space relative to your surroundings and continually updating that knowledge as you move. DeepMind scientists trained neural networks to navigate like this in a square arena, mimicking the paths that foraging rats took as they explored the space.

Read More
Google Duplex will call salons, restaurants, and pretend to be human for you [Updated]

Google Duplex will call salons, restaurants, and pretend to be human for you [Updated]

Read More