Apple Inc.

Benjamin Poulain

Richard J Mondello

Xiaojin Shi

Marco Zuliani

Samuel M Weinig

Adele C Peterson

Francesco Rossi

Jessie Berlin

Brian Weinstein

Alex Christensen

Vignesh Jagadeesh

Vinay Sharma

Xiaohuan Corina Wang

Brian Edward Walsh

Bartlomiej W Rymkowski

Omid Khalili

Alexey Marinichev

A method includes receiving input data at a trained machine learning model that includes a common part and task-specific parts, receiving an execution instruction that identifies one or more processing tasks to be performed, processing the input data using the common part of the trained machine learning model to generate intermediate data, and processing the intermediate data using one or more of the task-specific parts of the trained machine learning model based on the execution instruction to generate one or more outputs.

Machine learning model with conditional execution of multiple processing tasks

In various embodiments described herein, a content extension and programming interface enable third-party content extensions to supply transformation and filtering actions and associated criteria to native web clients on a system. In one embodiment, the native web client loads data for a third-party content filtering, blocking, or transformation extension and conducts extension defined actions without requiring additional intermediation by the third-party content. In one embodiment, a third-party application downloaded to a mobile or handheld device can include an extension data object that provides actions and triggers that are loaded by a native web client of the system. The third-party application is not required to execute continuously and can exit or be terminated once the web client retrieves the extension data object.

Web resource load blocking API

Artistic styles extracted from one or more source images may be applied to one or more target images, e.g., in the form of stylized images and/or stylized video sequences. The extracted artistic style may be stored as a plurality of layers in a neural network, which neural network may be further optimized, e.g., via the fusion of various elements of the network's architectures. An optimized network architecture may be determined for each processing environment in which the network will be applied. The artistic style may be applied to the obtained images and/or video sequence of images using various optimization methods, such as the use of scalars to control the resolution of the unstylized and stylized images, temporal consistency constraints, as well as the use of dynamically adjustable or selectable versions of Deep Neural Networks (DNN) that are responsive to system performance parameters, such as available processing resources and thermal capacity.

Flexible resolution support for image and video style transfer

Growing community of inventors

Cupertino, CA, United States of America

Benjamin Poulain