公开(公告)号：US10853700B2

公开(公告)日：2020-12-01

申请号：US16928949

申请日：2020-07-14

Applicant: Adobe Inc.

Inventor： Jayant Kumar ,  Zhe Lin ,  Vipulkumar C. Dalal

IPC: G06K9/62

Abstract: There is described a computing device and method in a digital medium environment for custom auto tagging of multiple objects. The computing device includes an object detection network and multiple image classification networks. An image is received at the object detection network and includes multiple visual objects. First feature maps are applied to the image at the object detection network and generate object regions associated with the visual objects. The object regions are assigned to the multiple image classification networks, and each image classification network is assigned to a particular object region. The second feature maps are applied to each object region at each image classification network, and each image classification network outputs one or more classes associated with a visual object corresponding to each object region.

公开(公告)号：US10733480B2

公开(公告)日：2020-08-04

申请号：US16039311

申请日：2018-07-18

Applicant: Adobe Inc.

Inventor： Jayant Kumar ,  Zhe Lin ,  Vipulkumar C. Dalal

IPC: G06K9/62

Abstract: There is described a computing device and method in a digital medium environment for custom auto tagging of multiple objects. The computing device includes an object detection network and multiple image classification networks. An image is received at the object detection network and includes multiple visual objects. First feature maps are applied to the image at the object detection network and generate object regions associated with the visual objects. The object regions are assigned to the multiple image classification networks, and each image classification network is assigned to a particular object region. The second feature maps are applied to each object region at each image classification network, and each image classification network outputs one or more classes associated with a visual object corresponding to each object region.

公开(公告)号：US20200342255A1

公开(公告)日：2020-10-29

申请号：US16928949

申请日：2020-07-14

Applicant: Adobe Inc.

Inventor： Jayant Kumar ,  Zhe Lin ,  Vipulkumar C. Dalal

IPC: G06K9/62

Abstract: There is described a computing device and method in a digital medium environment for custom auto tagging of multiple objects. The computing device includes an object detection network and multiple image classification networks. An image is received at the object detection network and includes multiple visual objects. First feature maps are applied to the image at the object detection network and generate object regions associated with the visual objects. The object regions are assigned to the multiple image classification networks, and each image classification network is assigned to a particular object region. The second feature maps are applied to each object region at each image classification network, and each image classification network outputs one or more classes associated with a visual object corresponding to each object region.

公开(公告)号：US20200026956A1

公开(公告)日：2020-01-23

申请号：US16039311

申请日：2018-07-18

Applicant: Adobe Inc.

Inventor： Jayant Kumar ,  Zhe Lin ,  Vipulkumar C. Dalal

IPC: G06K9/62

Abstract: There is described a computing device and method in a digital medium environment for custom auto tagging of multiple objects. The computing device includes an object detection network and multiple image classification networks. An image is received at the object detection network and includes multiple visual objects. First feature maps are applied to the image at the object detection network and generate object regions associated with the visual objects. The object regions are assigned to the multiple image classification networks, and each image classification network is assigned to a particular object region. The second feature maps are applied to each object region at each image classification network, and each image classification network outputs one or more classes associated with a visual object corresponding to each object region.