Track and label objects in images and video.

Identify content in images and video.

Identify and track hands and fingers.

Identify and recognize hand gestures.

Locate objects and create image masks with labels.

Select objects interactively and create image masks.

Identify faces in images and video.

Identify facial features for visual effects and avatars.

Find people and body positions.

Embed images into feature vectors.

Classify text into relevant tags.

Embed texts into feature vectors.

Identify the language of text.

Classify sounds into relevant tags.

Embed audio into feature vectors.