Realeyes Ou

Javier Orozco

Elnar Hajiyev

Martin Salo

Jeffrey F Cohn

Gábor Szirtes

István Petrás

Dániel Szolgay

Ákos Utasi

A computer-implement method of predicting commercial effectiveness of a piece of media content without collecting data from potential consumers. The method comprises extracting an information-rich content-based parameter from the media content. The parameter may be a vector having a predetermined, e.g. fixed, dimensionality that is designed as an input in a performance data prediction engine. By enabling the same type of parameter to be extracted from media content of different types and durations, the technique proposed allows media content for which performance data has already been gathered to be used to predict performance data for new media content. The prediction can be done based on a comparison of the content-based parameters extracted from media content. Alternatively, machine learning techniques may be used to generate a model using known performance data, whereby the model can use the content-based parameter from new media content to predict performance data.

Method and apparatus for immediate prediction of performance of media content

Methods and systems of predicting performance data for a piece of media content that is consumable by a user at a client device are provided. In one or more embodiments, the method collects raw input data, such as from a webcam, indicative of a user's response to the media content as the user watches the content. The data is processed to extract and obtain a series of head pose signals and facial expression signals, which is then input to a classification model. The model maps the performance data of the media content over time in response to the signals evaluated by the method to produce a prediction of the performance of the piece of media content.

Data processing methods for predictions of media content performance

Growing community of inventors

Tallinn, Estonia

Javier Orozco