Abstract:
A system and method for identifying trending content based on context. The method includes generating at least one signature for each of a plurality of multimedia content elements, wherein each signature represents a concept, wherein each concept is a collection of signatures and metadata describing the concept; correlating the concepts of the generated signatures to determine at least one context of each multimedia content element, wherein each context represents a sentiment; and identifying, based on the determined contexts, at least one trending multimedia content element, wherein the context of each trending multimedia content element meets a sentiment threshold.
Abstract:
A method and system for assigning a multimedia content element to a user. The method includes generating at least one signature to the multimedia content element; determining, based on the generated at least one signature, whether the multimedia content element exists in a database; and assigning a unique identifier of the user to the multimedia content element, when it is determined that the multimedia content element does not exist in the database.
Abstract:
Methods and apparatus for performing an action on a device based on audio are disclosed. An example method includes determining at a first device whether the audio includes a monitoring code indicating that the audio is to be monitored, generating a signature using a portion of the audio containing the monitoring code, and causing the action to be performed on a second device based on at least one of the monitoring code or the signature.
Abstract:
A system and method for recommending trending content based on context. The method includes receiving a query, wherein the query indicates a user intent; searching in at least one data source for a plurality of multimedia content elements related to the user intent; generating at least one signature for each of the plurality of multimedia content elements, wherein each signature represents a concept, wherein each concept is a collection of signatures and metadata describing the concept; correlating the concepts of the generated signatures to determine at least one context of each multimedia content element, wherein each context represents a sentiment; and generating, based on the determined contexts, a recommendation of at least one multimedia content element from among the plurality of multimedia content elements.
Abstract:
First and second receiver devices can receive different information, such as audio and video information, from the same source and corresponding to the same event. In an example that includes radio (audio only) and video broadcasts, the received audio broadcast information can be delayed relative to the received video broadcast information. An audio signal delay circuit can be configured to receive and delay reproduction of the audio broadcast information, such as based on a user-specified delay parameter. In an example, a processor circuit monitors the audio information in real-time for a specified event, such as an emergency alert, and notifies the listener substantially without delay.
Abstract:
Methods and apparatus to maintain audience privacy while determining viewing of video-on-demand (VOD) programs are disclosed. An example method disclosed herein comprises obtaining subscriber metering data from a site metering device monitoring presentation of VOD content at a first subscriber site, obtaining server metering data from a VOD server, the server metering data including identification information for a plurality of subscriber sites to identify particular VOD content provided uniquely to each of the subscriber sites, the identification information manipulated to preserve anonymity of the plurality of subscriber sites, manipulating at least a portion of the subscriber metering data to determine a first manipulated identifier to identify the first subscriber site, and using the first manipulated identifier to cross-reference the manipulated identification information included in the server metering data to merge the subscriber metering data and the portion of the server metering data uniquely associated with the first subscriber site.
Abstract:
A system and method for detecting a target area of user interest within a multimedia content element are provided. The method includes receiving the multimedia content element from a user computing device; partitioning the multimedia content element into a number of partitions, each partition having at least one object therein; generating at least one signature for each partition of the multimedia content element, wherein each of the at least one signatures for each partition represents a concept; determining a context of the multimedia content element based on the concepts; and identifying at least one partition of the multimedia content as a target area of user interest based on the context of the multimedia content element.
Abstract:
Methods and systems to perform methods comprising receiving, at a computer system from a first electronic device a first electronic media work; extracting one or more features therefrom; determining that at least a portion of the first electronic media work corresponds to a first reference media work based on a matching of the extracted features against a database of reference features; receiving, from a second electronic device, a query related to the first electronic media work; linking the query to action information in an action database based upon determining that at least a portion of the first electronic media work corresponds to the first reference media work; generating machine-readable instructions associated with the action to be performed based at least in part on the linking of the query to the action information; transmitting, to the second electronic device, the machine-readable instructions; and logging an event associated with the machine-readable instructions.
Abstract:
Small changes in a broadcast version of a base media item can be identified by performing a multi-level comparison of digital fingerprints. A fingerprint of a base media item is compared to a fingerprint of a media broadcast to determine whether a media item embedded in a broadcast is likely, to a first level of certainty, to be the base media item. A second, more stringent, match between the fingerprint of the base media item and loosely matched items can be used to identify potentially-altered versions of the base media item. Potentially-altered versions can be compared against each other, and resulting matches are flagged as altered base media items, which can be fingerprinted and tested against broadcast fingerprints in the same manner as the base media item.
Abstract:
Methods and apparatus to generate signatures representative of media are disclosed. An example method includes transforming a block of samples from a time-domain representation to a frequency-domain representation comprising multiple frequency bands, determining a signature function by fitting a curve to at least a subset of the frequency bands, and calculating signature values for the block. Calculating the tuple includes calculating a first angle between a reference line and a first line that is tangent to the signature function at a first index, calculating a second angle between the reference line and a second line that is tangent to the signature function at a second index, calculating a third angle between the reference line and a third line that is tangent to the signature function at a third index, and creating the signature values based on the first angle, the second angle, and the third angle.