Roku, Inc.

Thejaswi Hanumantha Raya

Sunil Ramesh

Michael Cutter

Neil Edward Johnson

Ramesh Babu Anaparti

Aravindkumar Ilangovan

Poornima Chozhiyath Raman

Iaroslav Zaitsev

Nima Rad

Disclosed herein are system, apparatus, device, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for creating high quality metadata and/or images for content. An example aspect operates by a computer-implemented method including receiving, from a plurality of sources, a set of metadata associated with an item of content. The method further includes determining a first quality metric for each metadata of the set of metadata, determining a set of quality metrics for attributes of each metadata of the set of metadata, and determining a second quality metric for each metadata of the set of metadata based on the set of quality metrics. The method further includes generating a final metadata based at least on the set of metadata, the first quality metric, and the second quality metric and providing the item of content and the final metadata associated with the item of content.

High quality metadata creation for content using noisy sources

Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for inserting objects in real-time into content based on frame identifiers. An example embodiment operates by identifying a first object in a frame of a content and generating an identifier for the first object in the frame. The identifier includes an array of numbers representing context and visual features of the first object in the frame. The example embodiments further operates by identifying a second object based on the array of numbers representing the first object and inserting the second object into the frame of the content.

Real-time objects insertion into content based on frame identifiers

In one aspect, an example method includes (i) obtaining input data, wherein the input data includes story description text; (ii) providing the obtained input data to a narration model and responsively receiving generated narrative text; (iii) identifying, from among the generated narrative text, a subset of text; (iv) providing the identified subset of text to an image generation model and responsively receiving generated images; (v) providing the generated images to an animation model and responsively receiving generated video segments; (vi) providing the generated narrative text to a text-to-speech model and responsively receiving generated narrative speech; (vii) combining the generated video segments and the generated narrative speech to generate video content; and (viii) outputting for presentation, the generated video content.

Video-content system with narrative-based video content generation feature

Growing community of inventors

Fremont, CA, United States of America

Thejaswi Hanumantha Raya