Adobe, Inc.

David Eldridge Benge

Max Gray Edell

Dylan DePass

Methods and systems are provided for training a neural network to track viewer engagement with a non-interactive display. Sensor data is obtained from one or more sensors, such as cameras, associated with a display device, and once a face is detected within the sensor data, a display sequence is initiated. The display sequence includes at least a first frame with a first visual feature and a second frame with a second visual feature. Using the sensor data obtained during presentation of the display sequence, viewer engagement with the sequence is tracked by determining eye movements and/or head movements. The detected eye movement and/or head movement is used to determine whether the person was actively engaged with the display sequence.

Training a neural network to track viewer engagement with non-interactive displays

In implementations of opting-in or opting-out of visual tracking, a computing device maintains digital images received for scanning, and includes an image scanning system that receives a digital image depicting one or more faces of persons captured in the digital image. The image scanning system is implemented to detect a face of a person who is depicted in the digital image from a scan of the digital image. The image scanning system can then scan the digital image for a visual tracking identifier that indicates a preference of the person for one of opting-in or opting-out of visual tracking. The image scanning system can detect the visual tracking identifier associated with the person from the scan of the digital image, and continue or discontinue the visual tracking of the person based on the visual tracking identifier indicating that the person opt-in or opts-out of visual tracking.

Opting-in or opting-out of visual tracking

Methods and systems are provided for tracking viewer engagement with a non-interactive display. Sensor data is obtained from one or more sensors, such as cameras, associated with a display device, and once a face is detected within the sensor data, a display sequence is initiated. The display sequence includes at least a first frame with a first visual feature and a second frame with a second visual feature. Using the sensor data obtained during presentation of the display sequence, viewer engagement with the sequence is tracked by determining eye movements and/or head movements. The detected eye movement and/or head movement is used to determine whether the person was actively engaged with the display sequence.

Tracking viewer engagement with non-interactive displays

Techniques for tracking pages accessed by an app executed to display multiple pages on a display. A computing device loads the app and present content from the app on a display. The computing device is configured to display individual pages of the app using declarative code specifying appearances of the pages. The computing device is configured to respond to events using page-generic imperative code. The computing device renders a page on the display using the declarative code of the page and identifies a tracking tag in the declarative code of the page. Based on identifying the tracking tag, the computing device sends a message to an analytics system identifying a page access.

Television application page tracking using declarative page tracking

A content management system (CMS) for graphically authoring and deploying a television app and pages for access and display by end user devices. The CMS displays a canvas in a GUI and receives input graphically specifying page appearance using a component on the canvas. The component is compatible for rendering in a webpage format and in a television app page format. The webpage format of the component is used for rendering the component on the canvas. The CMS deploys the page so it can be rendered in either the television app page format or the webpage format depending upon which type of page is requested. The CMS can also enable authoring and deploying configuration information and application logic that is accessed by a shell app on the end user devices.

Growing community of inventors

Poulsbo, WA, United States of America

David Eldridge Benge