Certain aspects of the present disclosure provide techniques for creating interactive digital experiences for linear content. This includes identifying a plurality of assets relating to presentation of linear content. It further includes generating interactive content using the linear content, including generating an interactive sequence referencing one or more of the plurality of assets and combining the linear content with the interactive sequence on a timeline sequentially describing the linear content. The timeline includes one or more branches relating to the linear content, and selection of a first branch of the one or more branches is based on the interactive sequence. It further includes transmitting the interactive content to a user.

The disclosed embodiments are directed toward local emotion detection during live streaming events. A client device receives a video stream from a remote server and captures media content while displaying the video stream. The client device uses a local machine learning/artificial intelligence event detection model to detect events in the media content. The client device then transmits detected events to the remote server involved in the live stream. The client device may additionally stream the locally captured media content to the remote server. In response, the remote server provides an interaction dashboard and, in some embodiments, mixes the local media content with the live stream.

Systems and methods for identifying certain objects within 360-degree content for user interaction. Objects within 360-degree content may be identified, and the corresponding segments of 360-degree content may be assigned a score according to how likely they may be to meet certain criteria, such as the likelihood that the user may interact with the object or its segment. Scores may be assigned in any manner, such as with reference to retrieved user information. In highly scored segments, users may be encouraged to pause the content at that segment, and interact with its objects. Encouragement may take any form, such as highlighting the segment or some component thereof. Likewise, interaction may also take any form, such as the allowing the user to alter the appearance of one or more segment objects in some way. In this manner, increased user interaction with 360-degree video is allowed, increasing viewer interest and engagement.

A computer-implemented is disclosed. The method includes: receiving media data of a live media stream; obtaining audience reaction data associated with the live media stream; identifying an event-of-interest in the live media stream based on the audience reaction data, wherein a time of the event-of-interest is prior to a time of the audience reaction data; obtaining a segment of at least one of audio data or video data of the live media stream that is associated with the time of the event-of-interest; generating a digital asset incorporating the segment; and providing the digital asset to at least one viewer of the live media stream.

Systems and methods create and distribute addressable virtual content with interactivity. The virtual content may depict a live event and may be customized for each individual user based on dynamic characteristics (e.g., habits, preferences, etc.) of the user that are captured during user interaction with the virtual content. The virtual content is generated with low latency between the actual event and the live content that allows the user to interactively participate in actions related to the live event. The virtual content may represent a studio with multiple display screens that each show different live content (of the same or different live events), and may also include graphic displays that include related data such as statistics corresponding to the live event, athletes at the event, and so on. The content of the display screens and graphics may be automatically selected based on the dynamic characteristics of the user.

A system and method for improved compression of a graphical user interface (GUI) receives a first graphical user interface (GUI), the GUI including a GUI object. The method further includes compressing the first GUI, wherein the compressed first GUI is associated with a first compression ratio; generating a second GUI based on the GUI object of the first GUI, wherein the second GUI is different from the first GUI; compressing the second GUI, wherein the compressed second GUI is associated with a second compression ratio; generating an instruction which when executed configures a computer device to render the second GUI, in response to determining that the second compression ratio is higher than the first compression ratio; and generating an instruction which when executed configures the computer device to render the first GUI, in response to determining that the second compression ratio is lower than the first compression ratio.

An apparatus, method and system including a processor, a memory device accessible by the processor, and circuitry to selectively communicate with an on-the-go user device located at a location different from a location of the apparatus. The memory device stores instructions to permit the apparatus to selectively serve as an at-home user device that receives data from a wireless ad hoc network formed by sensors located within a link range of the circuitry of the on-the-go user device, data from the sensors of the wireless ad hoc network providing data for consumption by the at-home user device to permit an at-home user to be immersed in an experience of the location of the on-the-go user device.

Embodiments of the present invention provide systems, methods, and computer storage media for editing images using a web-based intermediary between a user interface on a client device and an image editing neural network(s) (e.g., a generative adversarial network) on a server(s). The present image editing system supports multiple users in the same software container, advanced concurrency of projection and transformation of the same image, clubbing transformation requests from several users hosted in the same software container, and smooth display updates during a progressive projection.

Multiple scheduling producers such as content management systems, advertisement systems, and emergency broadcast systems can independently send scheduling events to scheduling consumers such as streaming servers, guide generators, and playlogs. The scheduling consumers maintain state machines with persistent storage to process scheduling events from scheduling producers and output media channel playlists, channel guides, and/or content. Scheduling producers can contribute independently to define a channel playout while information at scheduling consumers remains synchronized.

The present disclosure has a configuration in which a distributor who performs a separate distribution that is different from this live content, or a viewer who views this separate distribution can participate in a virtual space and express intent or participate in visual recognition through the commitment of a virtual item.