Adobe, Inc.

Vikas Yadav

Balaji Krishnamurthy

Mausoom Sarkar

Rajiv Mangla

Gitesh Malik

Sachin Soni

Anmol Dhawan

Ashish Duggal

Alok Kumar Singh

A method for clustering product media files is provided. The method includes dividing each media file corresponding to one or more products into a plurality of tiles. The media file include one of an image or a video. Feature vectors are computed for each tile of each media file. One or more patch clusters are generated using the plurality of tiles. Each patch cluster includes tiles having feature vectors similar to each other. The feature vectors of each media file are compared with feature vectors of each patch cluster. Based on comparison, product groups are then generated. All media files having comparison output similar to each other are grouped into one product group. Each product group includes one or more media files for one product. Apparatus for substantially performing the method as described herein is also provided.

Clustering product media files

Embodiments of the present invention provide systems and methods for automatically generating a shoppable video. A video is parsed into one or more scenes. Products and their corresponding product information are automatically associated with the one or more scenes. The shoppable video is then generated using the associated products and corresponding product information such that the products are visible in the shoppable video based on a scene in which the products are found.

Generating a shoppable video

Systems and methods are provided for intelligently adapting content presented in electronic forms. In some embodiments, a processor provides access to multiple instances of a first version of an electronic form by multiple clients based on determining that insufficient data exists in a data source for a category of information. The first version of the form can include content for soliciting data associated with the category of information. The processor can receive responsive electronic communications in response to providing access to the first version of the form. The processor can provide access to multiple instances of a second version of the electronic form by multiple clients based on determining from the received responses whether sufficient data exists for the category of information. The second version of the electronic form can omit or replace the content for soliciting data associated with the category of information.

Adaptive modification of content presented in electronic forms

A method for associating user engagement data with various features of a product associated with a webpage is provided. The method includes detecting a visit to a portion of the webpage by a user. The webpage includes features of the product. A feature from the portion of the webpage is then determined using keyword of the feature. The portion includes the keyword of the feature. A user engagement input is then received for entire webpage from the first user. The webpage includes only one user interface option to provide the user engagement input of a particular type, at an instance, for entire webpage. The user engagement input is associated with the feature and not associated with other features on the webpage. A report indicating association of the user engagement input with the feature and non-association of the user engagement input with other features on the webpage is then generated.

Method and apparatus for associating user engagement data received from a user with portions of a webpage visited by the user

Method and apparatus for clustering product media files

Methods and apparatus for blending regions from multiple images to produce a blended image. An image blending module may obtain multiple digital images of a scene. A base image and a source image are selected, and a stroke is applied to the source image to indicate a desired region which is to be blended with the base image. A region in the source image is identified from the stroke using a segmentation technique such as a graph cut algorithm, and the identified region is blended with the corresponding region of the base image, for example using alpha blending. Additional strokes may be applied to the source image to select other regions to be blended with the base image. A different image may be selected as a source image, and a region from the different image may be selected for blending with the base image.

Methods and apparatus for blending images

Systems and methods are presented for generating a new digital output image by blending a plurality of digital input images capturing the same scene at different levels of exposure. Each new pixel for the new digital output image is derived from a group of corresponding aligned pixels from the digital input images. For each group of corresponding pixels from the digital input images, an average color value in a first color space is derived by taking a separate average across each color channel of the first color space. The resulting average color value in the first color space is modified in order to raise its corresponding color saturation value in a second color space. The new pixel's color value in the first color space is set to the modified average color value.

Color saturation-modulated blending of exposure-bracketed images

Systems and methods are presented for generating a new digital output image by blending a plurality of digital input images capturing the same scene at different levels of exposure. Each new pixel for the new digital output image is derived from a group of corresponding aligned pixels from the digital input images. In order to determine a weight for each pixel in each group of mutually-aligned source-image pixels, a weight distribution function is applied to values of an image characteristic for the pixels in the group of corresponding aligned pixels, and a net weight is subsequently assigned to each of the pixels in the group. Pixel values of pixels in each group of mutually-aligned source-image pixels are modified based on the net weights assigned to the pixels in order to obtain a new pixel value for a corresponding new pixel in the new digital output image.

Blending of exposure-bracketed images using weight distribution functions

Seamless image compositions may be created. A plurality of images may be received, one image being a base image and the remaining image or images being source images. A selection may be received of one or more regions of one or more of the sources images to be copied onto the base image. An input may be received setting a blend parameter for each of the selected regions. The plurality of images may be blended together into a composite image by matching image gradients across one or more seams of the composite image. The image gradients may be based on the blend parameters. In one embodiment, input may be received to set a modified blend parameter for at least one of the selected regions and the plurality of images may be re-blended into a composite image in a similar manner but using the modified blend parameter.

Growing community of inventors

Noida, India

Vikas Yadav