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 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.

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.

The present disclosure provides a system and method for enabling navigation to one or more discrete segments of a real time dynamic and adaptive non-linear, non-sequentially assembled video. The method includes reception of a set of preference data associated with a user from a pre-defined selection criteria and a set of user authentication data. Accordingly, the method includes fetching of one or more tagged videos related to the set of preference data. The method includes fragmentation of the one or more tagged videos into the one or more tagged fragments. Further, the method includes clustering of one or more mapped fragments in a pre-defined order of preference. Furthermore, the method includes insertion of one or more interactive navigation options in one or more regions. Also, the method includes serving of the assembled video and inserted one or more interactive navigation options to the user.

The present invention provides a media player configurable to provide the user with a seamless way of conducting transactions from within a window of the media player itself. All intermediate steps relating to the required transaction are carried out by calling up relevant modules/applications from within the application libraries from within an e-commerce platform. In preferred embodiments, the media player is configured to retrieve an encoded media file from a server or other content delivery network (CDN). The media player is further configured to display predefined overlays to the user during playback of the media file in response to identifying cues encoded into the media file by the content owner. The content owner can upload the media files to a server or other CDN via a dashboard/user interface. The cues can be encoded with a plurality of fields to enable the desired functionality to be achieved.

A server computing device receives, from a client device, a digest segment generated by the client device. The digest segment corresponds to a first media stream segment received by the client device, and the digest segment includes a representation of the first media stream segment. The server computing devices determines, using the digest segment, a playback command that corresponds to the first media stream segment and transmits, to the client device, the playback command.

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 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.

Personal content server apparatus and associated methods that allow a user (e.g., cable or satellite network subscriber) to access content, such as a video program, from a location outside the subscriber's network. In one embodiment, a personal content server streams the content to the subscriber over a network connection from the local e.g., (subscription) network to a remote network upon authorization by a content manager process. Various access, business or operational rules are applied depending on the content and delivery mode; e.g., to live video broadcast, video-on-demand (VOD), or archived content from the subscriber's digital video recorder (DVR) or networked PVR. Secondary content (e.g., promotions, advertisements, etc.) can also be selectively replaced if desired in order to make the remotely delivered content more appropriate to the remote user's context.