Dropbox, Inc.

Leonard Fink

Daniel Wagner

Jan Senderek

David J Kriegman

Peter Neil Belhumeur

Bradley Neuberg

The present disclosure is directed toward systems and methods that provide users with efficient and effective user experiences when browsing, selecting, or inspecting content items. More specifically, systems and methods described herein provide users the ability to easily and effectively select multiple content items via a single touch gesture (e.g., swipe gesture). Additionally, systems and methods disclosed herein can allow users to select various content items in a selection interface, preview a content item, and return to the selection interface with the previous selections remaining in tact. Still further, systems and methods described herein allow users to transition between a content graphical user interface and a selection interface based on touch gestures with content items.

Browsing and selecting content items based on user gestures

The present disclosure relates to generating computer searchable text from digital images that depict documents utilizing an orientation neural network and/or text prediction neural network. For example, one or more embodiments detect digital images that depict documents, identify the orientation of the depicted documents, and generate computer searchable text from the depicted documents in the detected digital images. In particular, one or more embodiments train an orientation neural network to identify the orientation of a depicted document in a digital image. Additionally, one or more embodiments train a text prediction neural network to analyze a depicted document in a digital image to generate computer searchable text from the depicted document. By utilizing the identified orientation of the depicted document before analyzing the depicted document with a text prediction neural network, the disclosed systems can efficiently and accurately generate computer searchable text for a digital image that depicts a document.

Generating searchable text for documents portrayed in a repository of digital images utilizing orientation and text prediction neural networks

One or more embodiments provide features for managing and editing content items. In particular, one or more embodiments enable one or more users to access and modify content items from one of multiple client devices without requiring storage of the content item locally on the client device. Additionally, one or more embodiments enable storing reduced resolution content items on multiple client devices in a way that saves storage space on the client devices while providing access to a content item without requiring constant network access to a central system. Further, one or more embodiments enable globally applying local edits to a content item and corresponding reduced resolution content items on multiple client devices.

Growing community of inventors

San Francisco, CA, United States of America

Leonard Fink