(57) ABSTRACT A method includes selecting at least two objects within a primary video
stream, generating a first video stream from the primary video stream that includes a first of …

(57) ABSTRACT A method includes receiving information that identifies a reference position
in a location space. The method also includes receiving data that identifies one among a …

An approach is provided for selecting training observations for machine learning models.
The approach involves deter mining a first distribution of a plurality of features observed in …

(57) ABSTRACT A method of image retrieval includes obtaining information identifying a
plurality of selected objects and selecting one among a plurality of candidate geometrical …

(57) ABSTRACT A method of generating metadata includes using at least one digital image
to select a plurality of objects, wherein the at least one digital image depicts the plurality of …

BACKGROUND As the Internet becomes integrated into almost every aspect of people's
lives, the amount of content users provide is growing at an exponential rate. It is common for …

The present disclosure relates to systems and methods for classifying videos based on
video content. For a given video file including a plurality of frames, a subset of frames is …

(57) ABSTRACT A arbitrated image classifier can be trained to identify whether an image
contains specified features, such as sexual, violent, or other potentially objectionable …

Multimodal data mining in a multimedia database is addressed as a structured prediction
problem, wherein map ** from input to the structured and interdependent output variables …

Methods, systems, and apparatus, including computer programs encoded on computer
storage media for evaluating robot learning. In some implementations, a system receives …