Abstract:
A system and methodology provide for annotating videos with entities and associated probabilities of existence of the entities within video frames. A computer-implemented method identifies an entity from a plurality of entities identifying characteristics of video items. The computer-implemented method selects a set of features correlated with the entity based on a value of a feature of a plurality of features, determines a classifier for the entity using the set of features, and determines an aggregation calibration function for the entity based on the set of features. The computer-implemented method selects a video frame from a video item, where the video frame having associated features, and determines a probability of existence of the entity based on the associated features using the classifier and the aggregation calibration function.
Abstract:
One or more techniques and/or systems are provided for metadata tag evaluation. For example, a metadata tag, associated with content, may be identified (e.g., a hashtag #ML may be used to tag a social network post). A set of characters, within the content, may be evaluated utilizing a probability matrix and the content to identify an expanded metadata tag (e.g., an expanded hashtag "machine learning"). Descriptive content, such as websites, articles, social network posts, and/or other content associated with the expanded metadata tag, may be retrieved. A description for the metadata tag may be generated based upon the descriptive content (e.g., a definition for machine learning). In this way, the description, related metadata tags, and/or supplemental content may be provided to users having an interest in learning about the metadata tag.
Abstract:
A database of video clips is provided wherein each video clip depicts normal or abnormal behavioral patterns in children aged from birth and older or in adults. The behavior patterns in the video clip database are relevant to neurodevelopmental disorders. The behavior patterns depicted in the video clips are indexed and searchable. Also provided is a method of assessing a behavioral abnormality in the test subject. The normal and abnormal patterns for a given behavior can be compared to a test subject performing the same behavior depicted in the video library, to permit a medical professional to assess the extent of a behavioral abnormality in the test subject.
Abstract:
Ways to generate, store, and distribute optimized content are described. Content modification operations including color correction are stored as metadata that is embedded in each content item. The metadata is extracted in order to eliminate or update the modification operations. Modification operations are updated based at least partly on profiles associated with one or more content provision elements. The profiles include device profiles and codec profiles. Each profile may be specific to a particular element or be a generic profile associated with multiple elements. The profiles are generated based on evaluation of the devices and codes and are stored as entries in a look up table. When content is provided, the profiles are used to optimize the content for display.
Abstract:
A system, method, and software application to tag digital data/content with voice and/or icons/images. The user performs a series of actions on his user device to enable tagging of data/content with voice and/or icons/images. The voice tags are user- spoken words associated with specified data entities, while the icon/image tags are user-selected digital images or icons linked to data sets stored on the user device or on the network. The voice and/or icon tags are defined in an interactive and dynamic way and intelligently processed by a system consistent with the present invention and later used to retrieve content linked to them.
Abstract:
A method and system to facilitate identifying and recording capture location of recorded video. A computing system determines multiple locations where a first wireless communication module and second wireless communication module have lost wireless connectivity with each other, as possible locations where a video camera may be used to capture video. The computing system then outputs, for presentation to the videographer or another user, a location-selection prompt that specifies the multiple determined locations as candidate capture-locations for a video that was captured by the video camera. Further, the computing system receives, in response to the location-selection prompt, data that represents a user selection of one of the specified locations. The computing system then records the selected location as capture-location metadata for the video, such as capture-location data integrated with the video or in a database relationship with the video.
Abstract:
A technique for media personalization commences with users creating personal lists of media assets with their own labels. The lists, or containers, are voted upon by other users who can assign a vote to a container. An overall ranking of the labelled container can be assigned based on user voting. When a list of containers is presented as a choice to users, a selection is made. The media assets associated with the selected container are presented, and along with each media asset, at least one other additional container is presented for display. In one exemplary embodiment, the highest ranked additional labelled container that also contains each media asset is displayed along with the asset. Users can then select this additional container to display its media assets and their additional containers.