The present disclosure relates to systems, methods, and non-transitory computer readable media for training and utilizing a generative machine learning model to select one or more treatments for a client device from a set of treatments based on digital characteristics corresponding to the client device. In particular, the disclosed systems can train and apply a variational autoencoder with a task embedding layer that generates estimated effects for treatment combinations. For example, the disclosed systems receive, as input, digital characteristics corresponding to the client device and various treatment combinations. The disclosed systems apply the trained generative machine learning model with the task embedding layer to the digital characteristics to generate effect estimations for the various treatment combinations. Based on the effect estimations for the treatment combinations, the disclosed systems select one or more treatments to provide to the client device.

A system and method for displaying digital media files with compulsory advertisement files is disclosed. In one embodiment, the system includes a user interface, a media file decryptor, an ad manager, an intersplicer, and a media player. The user interface receives input from a user indicating the selection of media files to be presented. The media file decryptor receives and decrypts the selected media files. The ad manager receives and manages ad files from an ad file source. The intersplicer combines the media files with the ad files by providing control signals to the media player, causing the media player to present the ad files with the selected media files. Various embodiments of the invention facilitate the wide distribution of media content in a way that allows the free use of media properties, on demand, with direct consumer exchange capabilities, while at the same time enabling compensation to copyright holders.

Methods, systems, and apparatus, including a media player and computer-readable mediums, are described for rendering media content at a frame rate that is safe to a user. A system, or its media player, obtains media content that includes video content having multiple frames. The system determines a frame rate representing a rate for sequentially displaying the frames to the user when the media player plays the media content. Image content of each frame is scanned and data describing different photosensitivity thresholds is obtained. Based on a photosensitivity of the user, the system determines that one or more frames in a portion of the media content include image content that is unsafe to the user when the media player plays the media content. The system selectively decreases a frame playback rate for the portion of the media content as a function of an input value that is selectable by the user.

Data processing engines are provided that include an electronic display, a decoding functionality selector, a decoding functionality generator in communication with the decoding functionality selector, and a decoding functionality verifier, each configured as described anywhere herein. Related methods of automatically constructing platform-independent decoders for encoded digital data encoded in particular formats are also provided as described anywhere herein.

An electronic apparatus includes: a signal receiver configured to receive a signal; a display; a communicator configured to communicate with an external apparatus; and a processor configured to: receive a signal of content corresponding to one format among a plurality of formats, request and receive playback information about the content corresponding to the format of the content from a server, perform a playback process with regard to the received signal of the content based on the playback information received from the server, and control the display to display an image of the content.

A terminal for receiving streaming data may receive information of a plurality of different quality versions of an image content; request, based on the information, a server for a version of the image content from among the plurality of different quality versions of the image content; when the requested version of the image content and artificial intelligence (AI) data corresponding to the requested version of the image content are received, determines whether to perform AI upscaling on the received version of the image content, based on the AI data; and based on a result of the determining whether to perform AI upscaling, performs AI upscaling on the received version of the image content through a upscaling deep neural network (DNN) that is trained jointly with a downscaling DNN of the server.

A terminal for receiving streaming data may receive information of a plurality of different quality versions of an image content; request, based on the information, a server for a version of the image content from among the plurality of different quality versions of the image content; when the requested version of the image content and artificial intelligence (AI) data corresponding to the requested version of the image content are received, determines whether to perform AI upscaling on the received version of the image content, based on the AI data; and based on a result of the determining whether to perform AI upscaling, performs AI upscaling on the received version of the image content through a upscaling deep neural network (DNN) that is trained jointly with a downscaling DNN of the server.

Systems and methods for broadcasting a video stream are disclosed. The systems and methods can receive a video stream from a broadcaster, process the video steam, store the video streaming, and deliver the video stream to a viewer as a live video stream or a video on demand. The viewer may use an access token to access the video stream. The systems and methods may include an error detection mechanism for detecting an interrupt in the video stream. The systems and methods can restore the access token to its original state if an error is detected. The systems and methods can also include one or more link sharing mechanisms for sharing links to a video stream. The shareable links may be associated with share tokens.

An artificial intelligence (AI) decoding apparatus includes a memory storing one or more instructions, and a processor configured to execute the stored one or more instructions, to obtain image data corresponding to a first image that is encoded, obtain a second image corresponding to the first image by decoding the obtained image data, determine whether to perform AI up-scaling of the obtained second image, based on the AI up-scaling of the obtained second image being determined to be performed, obtain a third image by performing the AI up-scaling of the obtained second image through an up-scaling deep neural network (DNN), and output the obtained third image, and based on the AI up-scaling of the obtained second image being determined to be not performed, output the obtained second image.

A device for processing video data can be configured to receive a configuration record for decoding a bitstream of the video data, wherein the configuration record for the bitstream includes a toolset indication syntax element that includes information identifying, from a set of video decoding tools, tools that are required to decode the bitstream associated with the configuration record; based on the toolset indication syntax element, determine whether to retrieve the bitstream associated with the configuration record; and based on the determination to retrieve the bitstream associated with the configuration record, retrieve the bitstream and outputting the bitstream to a video decoder for decoding.