Abstract: Methods, apparatus, systems and articles of manufacture to credit unidentified media are disclosed. Disclosed example apparatus include a database updater to store a first group of signatures representative of unidentified media in a database, the first group of signatures obtained from a first media meter to monitor a first media presentation device, the first group of signatures associated with a first media exposure category based on media source information reported by the first media meter. Disclosed example apparatus also include a media comparator to compare a second group of signatures with the first group of signatures, the second group of signatures obtained from a second media meter to monitor a second media presentation device. Disclosed example apparatus further include a reporter to credit media exposure represented by the second group of signatures to the first media exposure category when the second group of signatures matches the first group of signatures.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to generate a signature based on signature candidates. An example apparatus disclosed herein includes first means for determining an alignment point of a first candidate signature segment and a second candidate signature segment, the first candidate signature segment and the second candidate signature segment include time data and signature data, the alignment point based on the time data of the first candidate signature segment and the time data of the second candidate signature segment, means for comparing a first signature to a second signature at the alignment point, the first signature representative of media included in the first candidate signature segment, the second signature included in the second candidate signature segment, and means for stitching the second signature to the first signature based on the comparison to generate a stitched signature, the stitched signature to be used for media crediting.

Abstract: Methods and apparatus to measure audience composition and recruit audience measurement panelists are disclosed. An example server disclosed herein includes processor circuitry to execute instructions to: provide a first code for embedding in a video stream of media to be distributed to a media device, the first code, when decoded by the media device, to cause the media device to transmit a report including an Internet Protocol (IP) address of the media device; determine, based on the IP address, a geographic region associated with the media device; determine that the geographic region is underrepresented in an audience measurement panel; and transmit, to the media device, an instruction to provide an enrollment request to join the audience measurement panel for display via the media device.

Abstract: In one example, a method is disclosed. The method includes, for each meter hash key of multiple meter hash keys generated from meter signatures in aggregated meter data: identifying a set of reference hash keys that match the meter hash key, and storing ones of the set of reference hash keys in respective data structures corresponding to media assets represented by the ones of the set of reference hash keys, where a first one of the data structures includes a sequence of reference hash keys that matches a corresponding sequence of meter hash keys. The method further includes: determining that the sequences of hash keys satisfy a validation criteria, and determining that the first one of the sequence of reference hash keys corresponds to a valid hash key match based on the determination that the sequences of hash keys satisfy the validation criteria.

Abstract: A method of encoding streamed data for use in training a model using a neural network includes ingesting a first streamed dataset corresponding to a first data epoch, updating a streamed dictionary using the first streamed dataset to generate a first dictionary snapshot corresponding to the first data epoch, and encoding the first streamed dataset using the first dictionary snapshot to generate a first encoded dataset. A program may be stored in non-transitory computer-readable media. The program may include instructions that, when executed by one or more processors, encode streamed data for use in training a model using a neural network by performing the method. A synthetic data generation system may include a streamed data source, an encoding storage configured to store a streamed dictionary, the one or more processors, and the non-transitory computer-readable media.

Abstract: Methods, apparatus, systems and articles of manufacture to perform media device asset qualification are disclosed. An example apparatus includes at least one memory, and at least one processor to execute instructions to at least identify a first set of candidate media device assets for disqualification, the candidate media device assets including A) a signature and B) a media identifier that identifies media, generate a hash table using a second set of the candidate media device assets, determine one or more counts of matches between C) a first signature and a first media identifier of a first candidate media device asset of the second set and D) respective signatures and media identifiers of multiple ones of the second set using the hash table, the multiple ones of the second set not including the first candidate media device asset, and load the first signature into a reference database as a reference signature.

Abstract: Apparatus, systems, articles of manufacture, and methods to identify media using watermarks and signatures are disclosed. An example apparatus includes at least one memory, instructions, and processor circuitry to execute the instructions to: determine a first time and a category indicated by a watermark detected in the media, determine a search window based on the first time indicated by the watermark, the search window to at least one of (i) extend a first duration of time before the first time indicated by the watermark or (ii) extend a second duration of time after the first time indicated by the watermark, and compare (i) a query signature associated with a second time within the search window with (ii) a subset of reference signatures associated with the category to identify the media, the query signature generated from the media, the subset of reference signatures generated from reference media associated with the category.

Abstract: Methods, apparatus, systems and articles of manufacture to credit media segments shared among multiple media assets are disclosed. Example methods disclosed herein include comparing a sequence of media signatures with a library of reference signatures to determine a signature match, the media signatures representative of a media presentation. Disclosed example methods also include determining duration and offset of the signature match, the offset to represent a position of the signature match relative to a start of a reference media asset associated with the signature match. Disclosed example methods further include crediting a segment of the media presentation represented by the signature match to an identifier of a class of media assets including the reference media asset in response to a determination that (i) the duration of the signature match does not exceed a first threshold and (ii) the offset does not exceed a second threshold.

Abstract: In one example, a method is disclosed. The method includes, for each meter hash key of multiple meter hash keys generated from meter signatures in aggregated meter data: identifying a set of reference hash keys that match the meter hash key, and storing ones of the set of reference hash keys in respective data structures corresponding to media assets represented by the ones of the set of reference hash keys, where a first one of the data structures includes a sequence of reference hash keys that matches a corresponding sequence of meter hash keys. The method further includes: determining that the sequences of hash keys satisfy a validation criteria, and determining that the first one of the sequence of reference hash keys corresponds to a valid hash key match based on the determination that the sequences of hash keys satisfy the validation criteria.

Abstract: Methods and apparatus to measure audience composition and recruit audience measurement panelists are disclosed. An example media device disclosed herein includes processor circuitry to execute instructions to: detect a first code embedded in a video stream of media presented by the media device, the first code to reference first audience measurement data to identify the media; after detection of the first code, provide a prompt to request input of second audience measurement data; and cause transmission of at least one of the first audience measurement data or the second audience measurement data to a remote data processing facility.

Abstract: Methods, apparatus, systems and articles of manufacture to credit unidentified media are disclosed. Disclosed example apparatus include a database updater to store a first group of signatures representative of unidentified media in a database, the first group of signatures obtained from a first media meter to monitor a first media presentation device, the first group of signatures associated with a first media exposure category based on media source information reported by the first media meter. Disclosed example apparatus also include a media comparator to compare a second group of signatures with the first group of signatures, the second group of signatures obtained from a second media meter to monitor a second media presentation device. Disclosed example apparatus further include a reporter to credit media exposure represented by the second group of signatures to the first media exposure category when the second group of signatures matches the first group of signatures.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to generate a signature based on signature candidates. An example apparatus disclosed herein includes first means for determining an alignment point of a first candidate signature segment and a second candidate signature segment, the first candidate signature segment and the second candidate signature segment include time data and signature data, the alignment point based on the time data of the first candidate signature segment and the time data of the second candidate signature segment, means for comparing a first signature to a second signature at the alignment point, the first signature representative of media included in the first candidate signature segment, the second signature included in the second candidate signature segment, and means for stitching the second signature to the first signature based on the comparison to generate a stitched signature, the stitched signature to be used for media crediting.

Abstract: Methods and apparatus to generate reference signatures are disclosed.

Abstract: Apparatus, systems, articles of manufacture, and methods to identify media using watermarks and signatures are disclosed. An example apparatus includes at least one memory, instructions, and processor circuitry to execute the instructions to: determine a first time and a category indicated by a watermark detected in the media, determine a search window based on the first time indicated by the watermark, the search window to at least one of (i) extend a first duration of time before the first time indicated by the watermark or (ii) extend a second duration of time after the first time indicated by the watermark, and compare (i) a query signature associated with a second time within the search window with (ii) a subset of reference signatures associated with the category to identify the media, the query signature generated from the media, the subset of reference signatures generated from reference media associated with the category.

Abstract: Example apparatus disclosed herein are to obtain a first hash key, a second hash key and a third hash key representative of first reference media in response to a first query of a first table, the second hash key associated with a second time preceding a first time associated with the first hash key, the third hash key associated with a third time following the first time associated with the first hash key. Disclosed example apparatus are also to prequalify the first hash key as a candidate for subsequent signature processing associated with a first site signature in response to a determination that the second hash key corresponds to a second site signature preceding the first site signature in time and that the third hash key corresponds to a third site signature following the first site signature in time.

Abstract: Methods, apparatus, systems and articles of manufacture to credit media segments shared among multiple media assets are disclosed. Example methods disclosed herein include comparing a sequence of monitored media signatures with a library of reference signatures to determine a signature match, the monitored media signatures representative of a monitored media presentation. Disclosed example methods also include determining duration and offset of the signature match, the offset to represent a position of the signature match relative to a start of a reference media asset associated with the signature match. Disclosed example methods further include crediting a segment of the monitored media presentation represented by the signature match to an identifier of a class of media assets including the reference media asset in response to a determination that (i) the duration of the signature match does not exceed a first threshold and (ii) the offset does not exceed a second threshold.

Abstract: Methods and apparatus to generate reference signatures are disclosed. An example method includes collecting a first signature for media being presented to a plurality of households; crediting the media when the first signature matches a reference signature in a reference signature database; in response to determining that the first signature does not match a reference signature in the reference signature database and the first signature does not match an unidentified signature in an unknown signature database, storing the first signature in the unknown signature database; in response to determining that a second signature does not match the reference signature in the reference signature database and the second signature matches the unidentified signature in the unknown signature database, and increasing a count associated with the unidentified signature.

Abstract: A method and system for measuring media-surfing activity. An example method includes a computing system receiving reporting of packet-data activity at a panelist site. Further, the example method includes the computing system using at least the received reporting of packet-data activity at the panelist site as a basis to detect occurrence of media-surfing activity at the panelist site, where the media-surfing activity comprises a user surfing through one or more content-selection menus. Still further, the example method includes the computing system reporting the detected occurrence of media-surfing activity at the panelist site as media-exposure data.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to identify candidates for media asset qualification. Example apparatus disclosed herein include a media creditor to determine whether to credit a first media asset to linear media or non-linear media, the non-linear media including subscription video on demand (SVOD). Disclosed example apparatus also include a media asset candidate controller to: classify the first media asset as a non-candidate for media asset qualification in response to the first media asset being credited to the linear media or the non-linear media. In some examples, the media asset candidate controller is to determine whether to classify the first media asset as a candidate for media asset qualification based on whether the first media asset remains uncredited by the media creditor and the first media asset overlaps a streaming period.

Abstract: Example methods, apparatus, systems and articles of manufacture are disclosed to facilitate meter to meter matching for media identification. Example apparatus disclosed herein include an unknown signature comparer, a stack counter, and a reference database updater. The unknown signature comparer is to select a candidate unknown signature segment meeting a threshold length from a set of unknown signature segments collected at a first audience measurement location, and compare individual signatures of the candidate unknown signature segment with a collection of unknown signature segments collected at a second audience measurement location. The stack counter is to count a number of times that the candidate unknown signature segment matches unknown signature segments in the collection, and identify the candidate unknown signature segment as a matched signature segment when the number of times meets a counter threshold.