A method for processing video data is performed by a data processing unit (DPU). The method includes obtaining, by the DPU of an edge device, video data; processing the video data to obtain video data chunks and indexing attributes; generating indexing metadata based on the video data chunks and the indexing attributes; processing the video data chunks and indexing attributes to generate contextual attributes; generating contextual metadata based on the contextual attributes and the video data chunks; associating the indexing metadata and the contextual metadata with the video data chunks; and storing the indexing metadata, contextual metadata, and the video data chunks in storage.

Mechanisms are provided for character-based and image-based media content search and discovery. Character images or entity images are mapped to corresponding media content. Selection of an image or a portion of an image may trigger or search for corresponding media content or begin playback of relevant media content. Character images or entity images need not correspond to a primary program character or object but may correspond to minor characters or tangential entities depicted periodically on particular programs.

Mechanisms are provided for character-based and image-based media content search and discovery. Character images or entity images are mapped to corresponding media content. Selection of an image or a portion of an image may trigger or search for corresponding media content or begin playback of relevant media content. Character images or entity images need not correspond to a primary program character or object but may correspond to minor characters or tangential entities depicted periodically on particular programs.

Exemplary embodiments relate to the creation of a media effect index for group video conversations. Media effect application (e.g., in the form of graphical overlays, filters, sounds, etc.) may be tracked in a timeline during a chat session. The resulting index may be used to create a highlights reel, which may serve as an index into a live show or may be used to determine the best time to insert materials into a recording of the conversation. The index may be used to automatically detect events in the video feed, to allow viewers to skip ahead to exciting moments (e.g., represented by clusters of applications of particular types of media effects), to determine where each participant spoke in a discussion, or to provide a common “watch together” experience while multiple users watch a common video. An analysis of the index may be used for research or consumer testing.

Exemplary embodiments relate to the creation of a media effect index for group video conversations. Media effect application (e.g., in the form of graphical overlays, filters, sounds, etc.) may be tracked in a timeline during a chat session. The resulting index may be used to create a highlights reel, which may serve as an index into a live show or may be used to determine the best time to insert materials into a recording of the conversation. The index may be used to automatically detect events in the video feed, to allow viewers to skip ahead to exciting moments (e.g., represented by clusters of applications of particular types of media effects), to determine where each participant spoke in a discussion, or to provide a common “watch together” experience while multiple users watch a common video. An analysis of the index may be used for research or consumer testing.

The present disclosure discloses a method and apparatus for determining video material of news. The method for determining video material of news comprises: recognizing a person name in a news text; searching a video based on the person name, to obtain a to-be-selected video; extracting a key frame in the to-be-selected video; recognizing a person in the key frame to obtain identity information of the person; and determining the to-be-selected video as video material of news, in response to the identity information of the person conforming to the person name. The present disclosure improves the consistency between the video material of the news and the news text.

The present disclosure discloses a method and apparatus for determining video material of news. The method for determining video material of news comprises: recognizing a person name in a news text; searching a video based on the person name, to obtain a to-be-selected video; extracting a key frame in the to-be-selected video; recognizing a person in the key frame to obtain identity information of the person; and determining the to-be-selected video as video material of news, in response to the identity information of the person conforming to the person name. The present disclosure improves the consistency between the video material of the news and the news text.

A first layer of data having a first set of Ambisonic audio components can be decoded where the first set of Ambisonic audio components is generated based on ambience and one or more object-based audio signals. A second layer of data is decoded having at least one of the one or more object-based audio signals. One of the object-based audio signals is subtracted from the first set of Ambisonic audio components. The resulting Ambisonic audio components are rendered to generate a first set of audio channels. The one or more object-based audio signals are spatially rendered to generate a second set of audio channels. Other aspects are described and claimed.

Upon capture of video data for a match of a sport at a first time, an apparatus performs detection of event information from the captured video data during a first time-period starting from the first time, where the event information includes information identifying an occurrence timing of an event that occurs in the match of the sport, an event type of the event, and an occurrence position of the event. The apparatus reproduces the video data, on a display screen, with a delay by a second time-period obtained by adding a third time-period longer than or equal to a predetermined time-period to the first time-period, and, upon detection of the event information, continues displaying the event type and the occurrence position of the event, for the predetermined time-period, from a timing that is the predetermined time before the occurrence timing of the event within the reproduced video data.

Upon capture of video data for a match of a sport at a first time, an apparatus performs detection of event information from the captured video data during a first time-period starting from the first time, where the event information includes information identifying an occurrence timing of an event that occurs in the match of the sport, an event type of the event, and an occurrence position of the event. The apparatus reproduces the video data, on a display screen, with a delay by a second time-period obtained by adding a third time-period longer than or equal to a predetermined time-period to the first time-period, and, upon detection of the event information, continues displaying the event type and the occurrence position of the event, for the predetermined time-period, from a timing that is the predetermined time before the occurrence timing of the event within the reproduced video data.