Abstract: In response to detecting a purchase of a first product by a user, a computer system determines a category of the first product. In response to determining the category of the first product, the computer system determines a blackout time period for the user based on a maximum revenue impact amount corresponding to the blackout time period, a probability that the first product will be repurchased, and a probability that the first product is purchased after an impression is viewed, and wherein the blackout time period corresponds to a time period where one or more impressions of at least the first product purchased by the user are not transmitted for display to the user. In response to determining the blackout time period for the user, the computer system causes the blackout time period to be applied to the user.

Abstract: The present disclosure relates to language agnostic unsupervised removal of text from form images. According to one embodiment, a method comprises generating a spectral domain representation of an image by applying a transformation, where the image depicts form layout elements and text elements, applying a first filter to the spectral domain representation to remove a portion of the frequency domain corresponding to the text element, and applying a transformation to the filtered spectral domain representation of the image to generate a reconstructed image. The text elements are not depicted in the reconstructed image.

Abstract: Techniques are disclosed for removing text from an image of a form document. The text is removed by determining a spectral domain representation of the image and applying a filter to remove the high-frequency components which correspond to the text in the form. An image is reconstructed from the filtered spectral domain representation which maintains the low-frequency components, while deemphasizing or removing the high-frequency components. A shape of the filter applied to the spectral domain representation is determined based on a similarity measure between the image of the form and the reconstructed image.

Abstract: The present disclosure relates to language agnostic unsupervised removal of text from form images. According to one embodiment, a method comprises generating a spectral domain representation of an image by applying a two dimensional frequency domain transformation, where the image depicts form layout elements and text elements. Applying a first filter to the spectral domain representation to remove a portion of the frequency domain corresponding to the text element, and applying an inverse two dimensional frequency domain transformation to the filtered spectral domain representation of the image to generate a reconstructed image. The text elements are not depicted in the reconstructed image.