公开(公告)号：US10664999B2

公开(公告)日：2020-05-26

申请号：US15897807

申请日：2018-02-15

Applicant: Adobe Inc.

Inventor： Prakhar Gupta ,  Sourav Pal ,  Shubh Gupta ,  Ritwik Sinha ,  Ajaykrishnan Jayagopal

IPC: G06T9/00 ,  G06T3/40 ,  G06N3/08 ,  G06F3/01 ,  G06T7/90 ,  G06T7/70

Abstract: A content saliency network is a machine-learned neural network that predicts the saliency of elements of a content item. The content saliency network may be used in a method that includes determining a set of elements in a UI and computing a first context vector for the content. The method may also include, for each element in the set of elements, computing a vector of simple features for the element, the simple features being computed from attributes of the element, computing a second context vector for the element, computing a third context vector for an intermediate context of the element, and providing the vectors to the content saliency network. The content saliency network provides a saliency score for the element. The method further includes generating an element-level saliency map of the content using the respective saliency scores for the set of elements and providing the saliency map to a requestor.

公开(公告)号：US20190147288A1

公开(公告)日：2019-05-16

申请号：US15814009

申请日：2017-11-15

Applicant: Adobe Inc.

Inventor： Prakhar Gupta ,  Shubh Gupta ,  Ritwik Sinha ,  Sourav Pal ,  Ajaykrishnan Jayagopal

IPC: G06K9/46 ,  G06K9/62 ,  G06Q30/02 ,  G06N3/08 ,  G06F3/01 ,  G06F17/30

Abstract: A content saliency network is a machine-learned neural network that predicts the saliency of elements of a content item. The content saliency network may be used in a method that includes determining a set of elements in draft content and computing a first pixel-level vector for the content. The method may also include, for each element in the set of elements, computing a vector of simple features for the element, the simple features being computed from attributes of the element, computing a second pixel-level vector for the element, computing a third pixel-level vector for an intermediate context of the element, and providing the vectors to the content saliency network. The content saliency network provides a saliency score for the element. The method further includes generating an element-level saliency map of the content using the respective saliency scores for the set of elements and providing the saliency map to a requestor.

公开(公告)号：US11263470B2

公开(公告)日：2022-03-01

申请号：US15814009

申请日：2017-11-15

Applicant: Adobe Inc.

Inventor： Prakhar Gupta ,  Shubh Gupta ,  Ritwik Sinha ,  Sourav Pal ,  Ajaykrishnan Jayagopal

IPC: G06K9/46 ,  G06K9/62 ,  G06Q30/02 ,  G06F3/01 ,  G06N3/08 ,  G06F16/958 ,  G06F16/35 ,  G06N3/04

Abstract: A content saliency network is a machine-learned neural network that predicts the saliency of elements of a content item. The content saliency network may be used in a method that includes determining a set of elements in draft content and computing a first pixel-level vector for the content. The method may also include, for each element in the set of elements, computing a vector of simple features for the element, the simple features being computed from attributes of the element, computing a second pixel-level vector for the element, computing a third pixel-level vector for an intermediate context of the element, and providing the vectors to the content saliency network. The content saliency network provides a saliency score for the element. The method further includes generating an element-level saliency map of the content using the respective saliency scores for the set of elements and providing the saliency map to a requestor.

公开(公告)号：US20190251707A1

公开(公告)日：2019-08-15

申请号：US15897807

申请日：2018-02-15

Applicant: Adobe Inc.

Inventor： Prakhar Gupta ,  Sourav Pal ,  Shubh Gupta ,  Ritwik Sinha ,  Ajaykrishnan Jayagopal

IPC: G06T9/00 ,  G06T3/40 ,  G06N3/08

Abstract: A content saliency network is a machine-learned neural network that predicts the saliency of elements of a content item. The content saliency network may be used in a method that includes determining a set of elements in a UI and computing a first context vector for the content. The method may also include, for each element in the set of elements, computing a vector of simple features for the element, the simple features being computed from attributes of the element, computing a second context vector for the element, computing a third context vector for an intermediate context of the element, and providing the vectors to the content saliency network. The content saliency network provides a saliency score for the element. The method further includes generating an element-level saliency map of the content using the respective saliency scores for the set of elements and providing the saliency map to a requestor.