Vision & Audio

Watching a run of frames to name what action is happening

Erasing a photo's background and keeping just the subject

The smallest box around an object, and where that box sits

A neural network built to spot patterns in a photo, layer by layer

Adding fitting color to a black-and-white picture

Technology that gets a computer to make sense of photos and video

The number a model attaches to how sure it is about its own answer

Sliding a small tile across a photo or other data to score each spot

Removing only the flecks mixed in, leaving the original untouched

Working out near and far from a single flat photo

Drawing a box around every face in a photo

Comparing faces to work out who someone is

A picture that lays scan results out in their original spots

A small value tile that carries what to look for

A 3D scene held as millions of scattered color blobs

Reading a hand or body movement as one predefined meaning

Following hand joint locations from one moment to the next

Looking at a picture and writing what's in it as a sentence

Putting one label on an entire photo

A point that pins down one location in an image

A numbered reference point at a fixed spot

Fitting mouth shapes to the beat of a sound

Turning body movement into a record of point locations

Turning a request or opening phrase into a song with AI

A 3D scene that answers with light for any spot and direction

Finding every object in a photo and boxing each one

Keeping the same number attached to the same thing over time

Reading the text in a picture and turning it into characters

Spotting the regularity that keeps repeating

Pinpointing how high or low a sound is

Shrinking a picture by keeping one representative value per region

Marking joint locations with points to work out a body's pose

Finishing a judgment on incoming input within a short, fixed window

The number of dots a picture is made of

Putting a label on every single pixel of a photo

Sticking one label on a short clip of sound

Splitting sound that's been mixed together back into its parts

Telling who spoke from the sound of their voice

A picture drawn so you can see sound with your eyes

The technology that transcribes spoken words into text

The conversion that turns sound into written words

The technology that reads text out loud in a voice

Using AI to enlarge a picture by inventing the detail it never had

Cutting a photo into pieces and treating it like text

The part that turns a sound blueprint into an actual waveform

An AI you speak commands to, and hear answers from

Imitating a person's voice from a short recording