公开(公告)号：US10762283B2

公开(公告)日：2020-09-01

申请号：US14947964

申请日：2015-11-20

Applicant: Adobe Inc.

Inventor： Natwar Modani ,  Vaishnavi Subramanian ,  . Utpal ,  Shivani Gupta ,  Pranav R. Maneriker ,  Gaurush Hiranandani ,  Atanu R. Sinha

IPC: G06F17/00 ,  G06F40/166 ,  G06F16/93 ,  G06F16/438 ,  G06F16/34 ,  G06N5/00 ,  G06N5/02 ,  G06F40/30 ,  G06N3/04 ,  G06N3/08

Abstract: Multimedia document summarization techniques are described. That is, given a document that includes text and a set of images, various implementations generate a summary by extracting relevant text segments in the document and relevant segments of images with constraints on the amount of text and number/size of images in the summary.

公开(公告)号：US10445783B2

公开(公告)日：2019-10-15

申请号：US14548061

申请日：2014-11-19

Applicant: Adobe Inc.

Inventor： Shivani Gupta ,  Gaurush Hiranandani ,  Anshul Agrawal ,  Charanjit Singh Ghai

IPC: G06Q30/02

Abstract: Target audience content interaction techniques are described. In one or more implementations, a plurality of content is quantified by one or more computing devices as a content feature representation for each of the plurality of content. A plurality of content feature clusters are generated by the one or more computing devices based at least in part on similarity of the content feature representations, one to another. Content cluster interaction data is also created by the one or more computing devices that describes interaction of each of a plurality of users with the plurality of content. A plurality of user interaction clusters are calculated from the content cluster interaction data by the one or more computing devices based at least in part on similarity of the content cluster interaction data of the plurality of users, one to another. The calculated plurality of user interaction clusters are employed by the one or more computing devices to determine content preferences of a target audience.