Abstract: Techniques for recommending media are described. A character preference function comprising a plurality of preference coefficients is accessed. A first character model comprises a first set of attribute values for the plurality of attributes of a first character. The first and second characters are associated with a first and second salience value, respectively. A second character model comprises a second set of attribute values for the plurality of attributes of a second character of the plurality of characters. A first character rating is calculated using the plurality of preference coefficients and the first set of attribute values. A second character rating of the second character is calculated using the plurality of preference coefficients with the second set of attribute values. A media rating is calculated based on the first and second salience values and the first and second character ratings. A media is recommended based on the media rating.

Abstract: Systems and methods to monitor and interact with users viewing screens are disclosed. An example system includes a sensor to gather gaze data from a user viewing images on a display. The display has spatial coordinates. The system includes a processor communicatively coupled to the display and the sensor. The processor determines a first gaze location having first spatial coordinates based on the gaze data and calibration settings associated with determining gaze locations. The processor alters a portion of the display at or near the first gaze location. After the portion of the display has been altered, the processor determines a second gaze location having second spatial coordinates based on the gaze data and the calibration settings. The processor performs a comparison of the first gaze location to the second gaze location.

Abstract: A content device and method is disclosed to include a processing device to process streaming video content. A fingerprinter receives captured frames of the streaming video content and, for each frame of a plurality of the captured frames, generates a one-dimensional histogram function of pixel values and transforms the histogram function with a Fast Fourier Transform (FFT), to generate a plurality of complex values for the frame. The fingerprinter further, for each of the plurality of complex values, assigns a binary one (“1”) when a real part of the complex value is greater than zero (“0”) and assigns a binary zero (“0”) when the real part is less than or equal to zero, to generate a plurality of bits. The fingerprinter further concatenates a specific number of the bits to generate a fingerprint for the frame.

Abstract: An example apparatus includes an impression logger to store mobile device impressions, the mobile device impressions corresponding to usage of a mobile device application to access first media; a classifier to determine whether a first number of detections of a first service set identifier (SSID) during a first time period satisfies a detection threshold, determine whether a second SSID was detected for a second time period that satisfies a time threshold, increment a counter when the detection threshold and the time threshold are satisfied, classify the first SSID as a vehicle SSID when the counter satisfies a quantity threshold; a logic circuit to, when the first SSID is a vehicle SSID, determine that at least one of the mobile device impressions occurred while the mobile device was in a vehicle.

Abstract: Methods and apparatus to identify a mood of media are disclosed. An example method includes accessing a known audio known to evoke a first emotion. A first synthesized sample is synthesized based on the known audio sample. A first value of a first feature of the first synthesized sample is calculated. A mood model is created based on the first feature. The mood model is to establish a relationship between the first feature and the first emotion. A second value of the first feature of first media evoking an unknown emotion is identified. The unknown emotion is identified as the first emotion when the mood model indicates that the second value corresponds to the first value.

Abstract: Methods and apparatus to monitor media exposure are disclosed. An example implementation includes accessing a meter identifier and first audio received from a wearable bracelet meter, the meter identifier uniquely associated with the wearable bracelet meter. Whether the first audio substantially matches second audio received at a second meter is determined. In response to determining that the first audio and the second audio substantially match, the meter identifier associated with the wearable bracelet meter and at least one of the first audio or the second audio are stored.

Abstract: Methods and apparatus to search datasets are disclosed. Example methods include in response to a search request including first and second logically related criteria, determining a first number of records in a database satisfying the first criterion and a second number of records in the database satisfying the second criterion; when the first number is less than the second number, selecting the first criterion as a basis for generating a subset of the records of the database; when the second number is less than the first number, selecting the second criterion as the basis for the identification of the subset of the records of the database; and searching the subset of the records.

Abstract: Methods and apparatus for classifying data for use in data fusion processes are disclosed. An example method of classifying data selectively groups nodes of a classification tree so that each node is assigned to only one of a plurality of groups and so that at least one of the groups includes at least two of the nodes. Data is classified based on the classification tree and the selective grouping of the nodes, and the results displayed.

Abstract: Example methods and apparatus to perform image classification based on pseudorandom features are disclosed. A disclosed example method includes generating first and second pseudorandom numbers, extracting a first feature of an image based on the first and second pseudorandom numbers, and determining a classification for the image based on the first extracted feature.