Method and apparatus for analyzing media content
AssigneeAT&T Intellectual Property I, L.P.
InventorRaghuraman Gopalan
Life of this patent
Estimating the term…
Abstract
Aspects of the subject disclosure may include, for example, a method for determining a first set of features in first images of first media content, generating a similarity score by processing the first set of features with a favorability model derived by identifying generative features and discriminative features of second media content that is favored by a viewer, and providing the similarity score to a network for predicting a response by the viewer to the first media content. Other embodiments are disclosed.
Claims20
A device, comprising:
- a processing system including a processor;
- and
- a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, comprising:
- generating a first set of image objects by filtering image objects scanned from first media content using first criteria, wherein the first criteria comprise a number of occurrences of an image object, a running time of occurrence of the image object, or a combination thereof;
- scanning a plurality of training images of a plurality of training media content items associated with a viewer to detect a plurality of training image objects;
- identifying a plurality of training visual features of the plurality of training image objects;
- generating a similarity model according to the plurality of training visual features;
- generating a similarity score by processing the first set of image objects with the similarity model;
- and
- providing the similarity score for predicting a response from equipment of the viewer regarding the first media content.
A machine-readable medium comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, comprising:
- generating a first set of image objects by filtering image objects scanned from first media content using first criteria, wherein the first criteria comprise a number of occurrences of an image object, a running time of occurrence of the image object, or a combination thereof;
- scanning a plurality of training images of a plurality of training media content items associated with a viewer to detect a plurality of training image objects;
- identifying a plurality of training visual features of the plurality of training image objects;
- generating a similarity model according to the plurality of training visual features;
- generating a similarity score by processing the first set of image objects with the similarity model;
- and
- generating a recommendation for the first media content according to the similarity score.
A method comprising:
- generating, by a processing system including a processor, a first set of image objects by filtering image objects scanned from first media content using first criteria, wherein the first criteria comprise a number of occurrences of an image object, a running time of occurrence of the image object, or a combination thereof;
- scanning, by the processing system, a plurality of training images of a plurality of training media content items associated with a viewer to detect a plurality of training image objects;
- identifying, by the processing system, a plurality of training visual features of the plurality of training image objects;
- generating, by the processing system, a similarity model according to the plurality of training visual features;
- and
- generating, by the processing system, a similarity score by processing the first set of image objects with the similarity model.
Dependencies are inferred from the claim text.